Daily Papers

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution by offloading KV cache management and parts of attention computation to the CPU. However, a key bottleneck remains: existing schedulers fail to effectively overlap CPU-offloaded tasks with GPU execution during the latency-critical, bandwidth-bound decode phase. This particularly penalizes real-time, decode-heavy applications (e.g., chat, Chain-of-Thought reasoning) which are currently underserved by existing systems, especially under memory pressure typical of edge or low-cost deployments. We present APEX, a novel, profiling-informed scheduling strategy that maximizes CPU-GPU parallelism during hybrid LLM inference. Unlike systems relying on static rules or purely heuristic approaches, APEX dynamically dispatches compute across heterogeneous resources by predicting execution times of CPU and GPU subtasks to maximize overlap while avoiding scheduling overheads. We evaluate APEX on diverse workloads and GPU architectures (NVIDIA T4, A10), using LLaMa-2-7B and LLaMa-3.1-8B models. Compared to GPU-only schedulers like VLLM, APEX improves throughput by 84% - 96% on T4 and 11% - 89% on A10 GPUs, while preserving latency. Against the best existing hybrid schedulers, it delivers up to 49% (T4) and 37% (A10) higher throughput in long-output settings. APEX significantly advances hybrid LLM inference efficiency on such memory-constrained hardware and provides a blueprint for scheduling in heterogeneous AI systems, filling a critical gap for efficient real-time LLM applications.

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context generation. While existing approaches offload KV caches to CPU memory or apply sparse attention to reduce GPU load, they often underutilize CPU compute resources and compromise accuracy. We present HGCA, a hybrid CPU-GPU attention mechanism that enables scalable, high-throughput LLM inference with near-full attention quality. HGCA performs dense attention on recently generated KV entries retained in GPU memory and parallel sparse attention on selected, salient KV entries in CPU memory. The attention outputs are efficiently merged using log-sum-exp fusion, minimizing PCIe transfer overhead. HGCA also introduces a finegrained, per-head sparsification strategy optimized for CPU execution, preserving contextual relevance while reducing computation. Our implementation seamlessly integrates into existing LLM frameworks without requiring model retraining. Experiments across diverse models and workloads show that HGCA achieves superior scalability, supports longer sequences and larger batch sizes, and outperforms existing sparse attention baselines in both performance and accuracy -- all on commodity GPU hardware.

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes present deployment challenges in resource-constrained environments with limited GPU memory capacity, as GPU memory is often insufficient to accommodate the full set of model weights. Consequently, typical deployments rely on CPU-GPU hybrid execution: the GPU handles compute-intensive GEMM operations, while the CPU processes the relatively lightweight attention mechanism. This setup introduces a key challenge: how to effectively optimize resource utilization across CPU and GPU? Prior work has designed system optimizations based on performance models with limited scope. Specifically, such models do not capture the complex interactions between hardware properties and system execution mechanisms. Therefore, previous approaches neither identify nor achieve the hardware limit. This paper presents MoE-Lens, a high-throughput MoE LLM inference system designed through holistic performance modeling for resource-constrained environments. Our performance model thoroughly analyzes various fundamental system components, including CPU memory capacity, GPU compute power, and workload characteristics, to understand the theoretical performance upper bound of MoE inference. Furthermore, it captures the system execution mechanisms to identify the key hardware bottlenecks and accurately predict the achievable throughput. Informed by our performance model, MoE-Lens introduces an inference system approaching hardware limits. Evaluated on diverse MoE models and datasets, MoE-Lens outperforms the state-of-the-art solution by 4.6x on average (up to 25.5x), with our theoretical model predicting performance with an average 94% accuracy.

This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a runtime system built on a graph-based abstraction that exposes optimization opportunities across stage-level parallelism, intra-request similarity, and inter-request skewness. These opportunities are realized through dynamic graph transformations, such as node splitting, reordering, edge addition, and dependency rewiring, applied to wavefronts of subgraphs spanning concurrent requests. The resulting execution plans are mapped onto hybrid CPU-GPU pipelines to improve resource utilization and reduce latency. Evaluations across a wide range of RAG workflows demonstrate speedups exceeding 1.5x and reaching up to 5x over existing frameworks, showcasing the effectiveness of coordinated generation and retrieval in serving environments.

The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. However, the large MoE model size still introduces substantial memory demands, which usually requires expert offloading on resource-constrained platforms and incurs significant overhead. Hybrid CPU-GPU inference has been proposed to leverage CPU computation to reduce expert loading overhead but faces major challenges: on one hand, the expert activation patterns of MoE models are highly unstable, rendering the fixed mapping strategies in existing works inefficient; on the other hand, the hybrid CPU-GPU schedule for MoE is inherently complex due to the diverse expert sizes, structures, uneven workload distribution, etc. To address these challenges, in this paper, we propose HybriMoE, a hybrid CPU-GPU inference framework that improves resource utilization through a novel CPU-GPU scheduling and cache management system. HybriMoE introduces (i) a dynamic intra-layer scheduling strategy to balance workloads across CPU and GPU, (ii) an impact-driven inter-layer prefetching algorithm, and (iii) a score-based caching algorithm to mitigate expert activation instability. We implement HybriMoE on top of the kTransformers framework and evaluate it on three widely used MoE-based LLMs. Experimental results demonstrate that HybriMoE achieves an average speedup of 1.33times in the prefill stage and 1.70times in the decode stage compared to state-of-the-art hybrid MoE inference framework. Our code is available at: https://github.com/PKU-SEC-Lab/HybriMoE.

This paper presents a comprehensive comparison of three dominant parallel programming models in High Performance Computing (HPC): Message Passing Interface (MPI), Open Multi-Processing (OpenMP), and Compute Unified Device Architecture (CUDA). Selecting optimal programming approaches for modern heterogeneous HPC architectures has become increasingly critical. We systematically analyze these models across multiple dimensions: architectural foundations, performance characteristics, domain-specific suitability, programming complexity, and recent advancements. We examine each model's strengths, weaknesses, and optimization techniques. Our investigation demonstrates that MPI excels in distributed memory environments with near-linear scalability for communication-intensive applications, but faces communication overhead challenges. OpenMP provides strong performance and usability in shared-memory systems and loop-centric tasks, though it is limited by shared memory contention. CUDA offers substantial performance gains for data-parallel GPU workloads, but is restricted to NVIDIA GPUs and requires specialized expertise. Performance evaluations across scientific simulations, machine learning, and data analytics reveal that hybrid approaches combining two or more models often yield optimal results in heterogeneous environments. The paper also discusses implementation challenges, optimization best practices, and emerging trends such as performance portability frameworks, task-based programming, and the convergence of HPC and Big Data. This research helps developers and researchers make informed decisions when selecting programming models for modern HPC applications, emphasizing that the best choice depends on application requirements, hardware, and development constraints.

GPUs are the most popular platform for accelerating HPC workloads, such as artificial intelligence and science simulations. However, most microarchitectural research in academia relies on GPU core pipeline designs based on architectures that are more than 15 years old. This paper reverse engineers modern NVIDIA GPU cores, unveiling many key aspects of its design and explaining how GPUs leverage hardware-compiler techniques where the compiler guides hardware during execution. In particular, it reveals how the issue logic works including the policy of the issue scheduler, the structure of the register file and its associated cache, and multiple features of the memory pipeline. Moreover, it analyses how a simple instruction prefetcher based on a stream buffer fits well with modern NVIDIA GPUs and is likely to be used. Furthermore, we investigate the impact of the register file cache and the number of register file read ports on both simulation accuracy and performance. By modeling all these new discovered microarchitectural details, we achieve 18.24% lower mean absolute percentage error (MAPE) in execution cycles than previous state-of-the-art simulators, resulting in an average of 13.98% MAPE with respect to real hardware (NVIDIA RTX A6000). Also, we demonstrate that this new model stands for other NVIDIA architectures, such as Turing. Finally, we show that the software-based dependence management mechanism included in modern NVIDIA GPUs outperforms a hardware mechanism based on scoreboards in terms of performance and area.

AMD GPUs offer state-of-the-art compute and memory bandwidth; however, peak performance AMD kernels are written in raw assembly. To address the difficulty of mapping AI algorithms to hardware, recent work proposes C++ embedded and PyTorch-inspired domain-specific languages like ThunderKittens (TK) to simplify high performance AI kernel development on NVIDIA hardware. We explore the extent to which such primitives -- for explicit tile-based programming with optimized memory accesses and fine-grained asynchronous execution across workers -- are NVIDIA-specific or general. We provide the first detailed study of the programming primitives that lead to performant AMD AI kernels, and we encapsulate these insights in the HipKittens (HK) programming framework. We find that tile-based abstractions used in prior DSLs generalize to AMD GPUs, however we need to rethink the algorithms that instantiate these abstractions for AMD. We validate the HK primitives across CDNA3 and CDNA4 AMD platforms. In evaluations, HK kernels compete with AMD's hand-optimized assembly kernels for GEMMs and attention, and consistently outperform compiler baselines. Moreover, assembly is difficult to scale to the breadth of AI workloads; reflecting this, in some settings HK outperforms all available kernel baselines by 1.2-2.4times (e.g., d=64 attention, GQA backwards, memory-bound kernels). These findings help pave the way for a single, tile-based software layer for high-performance AI kernels that translates across GPU vendors. HipKittens is released at: https://github.com/HazyResearch/HipKittens.

Large language model (LLM)-based inference workloads increasingly dominate data center costs and resource utilization. Therefore, understanding the inference workload characteristics on evolving CPU-GPU coupled architectures is crucial for optimization. This paper presents an in-depth analysis of LLM inference behavior on loosely-coupled (PCIe A100/H100) and closely-coupled (GH200) systems. We analyze performance dynamics using fine-grained operator-to-kernel trace analysis, facilitated by our novel profiler SKIP and metrics like Total Kernel Launch and Queuing Time (TKLQT). Results show that closely-coupled (CC) GH200 significantly outperforms loosely-coupled (LC) systems at large batch sizes, achieving 1.9x-2.7x faster prefill latency for Llama 3.2-1B. However, our analysis also reveals that GH200 remains CPU-bound up to 4x larger batch sizes than LC systems. In this extended CPU-bound region, we identify the performance characteristics of the Grace CPU as a key factor contributing to higher inference latency at low batch sizes on GH200. We demonstrate that TKLQT accurately identifies this CPU/GPU-bound transition point. Based on this analysis, we further show that kernel fusion offers significant potential to mitigate GH200's low-batch latency bottleneck by reducing kernel launch overhead. This detailed kernel-level characterization provides critical insights for optimizing diverse CPU-GPU coupling strategies. This work is an initial effort, and we plan to explore other major AI/DL workloads that demand different degrees of CPU-GPU heterogeneous architectures.

Modern GPUs feature specialized hardware units that enable high-performance, asynchronous dataflow execution. However, the conventional SIMT programming model is fundamentally misaligned with this task-parallel hardware, creating a significant programmability gap. While hardware-level warp specialization is the key to unlocking peak performance, it forces developers to manually orchestrate complex, low-level communication and software pipelines--a process that is labor-intensive, error-prone, and unsustainable. To address this challenge, we present Tawa, an automated compiler that systematically generates high-performance, warp-specialized code from a high-level, tile-based program. Central to our approach is a novel IR abstraction, asynchronous references (aref), which expresses warp-level communication without exposing low-level hardware details. Using this abstraction, Tawa automatically partitions programs into producer-consumer roles and manages the intricate dataflow pipeline, relieving developers of invasive kernel rewriting. Evaluation on NVIDIA H100 GPUs across representative LLM kernels shows that Tawa delivers high hardware utilization, achieving up to 1.1times speedup over highly optimized cuBLAS GEMM kernels. For attention workloads, Tawa attains 1.2times speedup over Triton and matches the performance of the hand-optimized CUTLASS C++ FlashAttention-3 kernel with far less programming effort.

Existing GPU libraries often struggle to fully exploit the parallel resources and on-chip memory (SRAM) of GPUs when chaining multiple GPU functions as individual kernels. While Kernel Fusion (KF) techniques like Horizontal Fusion (HF) and Vertical Fusion (VF) can mitigate this, current library implementations often require library developers to manually create fused kernels. Hence, library users rely on limited sets of pre-compiled or template-based fused kernels. This limits the use cases that can benefit from HF and VF and increases development costs. In order to solve these issues, we present a novel methodology for building GPU libraries that enables automatic on-demand HF and VF for arbitrary combinations of GPU library functions. Our methodology defines reusable, fusionable components that users combine via high-level programming interfaces. Leveraging C++17 metaprogramming features available in compilers like nvcc, our methodology generates a single and optimized fused kernel tailored to the user's specific sequence of operations at compile time, without needing a custom compiler or manual development and pre-compilation of kernel combinations. This approach abstracts low-level GPU complexities while maximizing GPU resource utilization and keeping intermediate data in SRAM. We provide an open-source implementation demonstrating significant speedups compared to traditional libraries in various benchmarks, validating the effectiveness of this methodology for improving GPU performance in the range of 2x to more than 1000x, while preserving high-level programmability.

Transformer-based Large Language Models (LLMs) have significantly advanced AI capabilities but pose considerable challenges for deployment on edge devices due to high computational demands, memory bandwidth constraints, and energy consumption. This paper addresses these challenges by presenting an efficient framework for deploying the Qwen2.5-0.5B model on the Xilinx Kria KV260 edge platform, a heterogeneous system integrating an ARM Cortex-A53 CPU with reconfigurable FPGA logic. Leveraging Activation-aware Weight Quantization (AWQ) with FPGA-accelerated execution pipelines, the proposed approach enhances both model compression rate and system throughput. Additionally, we propose a hybrid execution strategy that intelligently offloads compute-intensive operations to the FPGA while utilizing the CPU for lighter tasks, effectively balancing the computational workload and maximizing overall performance. Our framework achieves a model compression rate of 55.08% compared to the original model and produces output at a rate of 5.1 tokens per second, outperforming the baseline performance of 2.8 tokens per second.

Energy supply and heat dissipation are two of the main challenges with modern GPU deployments. While typically discussed in the context of new datacenter constructions, the same constraints also apply to small form-factor consumer devices, such as the DGX spark. In workloads characterized by alternating compute-intensive tasks such as matmuls with memory-bound operations such as norms or cross-entropy, the compute-intensive parts might hit power and/or thermal limits and start throttling. In this short paper, we show that chunking the workload into smaller parts that alternate compute and memory in higher frequencies, these power and temperature spikes can be smoothed out, preventing throttling and resulting in considerably faster wall-clock time and reduced total energy consumption. We present several scenarios in which this effect can be exploited on a DGX Spark with up to 2% performance and energy improvements, and demonstrate that the same phenomenon also happens on less constrained systems, such as a multi-GPU server, albeit at significantly reduced effect size of 1-2%.

Recent advances in large language models have brought immense value to the world, with their superior capabilities stemming from the massive number of parameters they utilize. However, even the GPUs with the highest memory capacities, currently peaking at 80GB, are far from sufficient to accommodate these vast parameters and their associated optimizer states when conducting stochastic gradient descent-based optimization. One approach to hosting such huge models is to aggregate device memory from many GPUs. However, this approach introduces prohibitive costs for most academic researchers, who always have a limited budget for many high-end GPU servers. In this paper, we focus on huge model fine-tuning on a single, even low-end, GPU in a commodity server, which is accessible to most AI researchers. In such a scenario, the state-of-the-art work ZeRO-Infinity suffers from two severe issues when running in a commodity server: 1) low GPU utilization due to inefficient swapping, and 2) limited trainable model size due to CPU memory capacity. The underlying reason is that ZeRO-Infinity is optimized for running on high-end GPU servers. To this end, we present Fuyou, a low-cost training framework that enables efficient 100B huge model fine-tuning on a low-end server with a low-end GPU and limited CPU memory capacity. The key idea is to add the SSD-CPU communication as an optimization dimension and thus carefully co-optimize computation and data swapping from a systematic approach to maximize GPU utilization. The experimental results show that 1) Fuyou is able to fine-tune 175B GPT-3 on a consumer GPU RTX 4090 with high GPU utilization, while ZeRO-Infinity fails to fine-tune; and 2) when training a small GPT-3 13B model, Fuyou achieves 156 TFLOPS on an RTX 4090 GPU while ZeRO-Infinity only achieves 45 TFLOPS.

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-scale models and infrequent requests. While existing solutions follow exclusive GPU deployment, we take a step back to explore modern platforms and find that: Emerging CPU architectures with built-in accelerators are capable of serving LLMs but remain underutilized, and both CPUs and GPUs can accommodate multiple LLMs simultaneously. We propose LLM-Mesh, a serverless inference scheme for small-to-mid-sized LLMs that enables elastic sharing across heterogeneous hardware. LLM-Mesh tackles three fundamental challenges: (1) precise, fine-grained compute resource allocation at token-level to handle fluctuating computational demands; (2) a coordinated and forward-looking memory scaling mechanism to detect out-of-memory hazards and reduce operational overhead; and (3) a dual approach that reduces resource fragmentation through proactive preemption and reactive bin-packing. Experimental results on 4 32-core CPUs and 4 A100 GPUs show that LLM-Meshimproves service capacity by 44% - 63% through sharing, while further leveraging CPUs boosts this to 91% - 159%.

The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating computational bottlenecks. Meanwhile, due to the cultivation of user programming habits and the high performance of GPUs, the CUDA ecosystem has established a dominant position in the field of parallel software. This dominance requires other hardware platforms to support CUDA-based software with performance portability. However, translating CUDA code to other platforms poses significant challenges due to differences in parallel programming paradigms and hardware architectures. Existing approaches rely on language extensions, domain-specific languages (DSLs), or compilers but face limitations in workload coverage and generalizability. Moreover, these methods often incur substantial development costs. Recently, LLMs have demonstrated extraordinary potential in various vertical domains, especially in code-related tasks. However, the performance of existing LLMs in CUDA transpilation, particularly for high-performance code, remains suboptimal. To address these challenges, we propose a novel framework for generating high-performance CUDA and corresponding platform code pairs, leveraging AI compiler and automatic optimization technology. We further enhance the framework with a graph-based data augmentation method and introduce HPCTransEval, a benchmark for evaluating LLM performance on CUDA transpilation. We conduct experiments using CUDA-to-CPU transpilation as a case study on leading LLMs. The speedup ratio of the CPU operators has an average improvemnet of 43.8\%, highlighting the potential of LLMs to address compatibility challenges within the CUDA ecosystem. Our code is available at https://github.com/PJLAB-CHIP/HPCTransCompile.

AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this request-level abstraction is fundamentally mismatched to compound AI workloads, and propose a shift to program-level scheduling: treating the entire agent workflow (not individual inference calls) as the first-class schedulable unit. We present SAGA, a distributed scheduler that implements this abstraction through three mechanisms: (1) Agent Execution Graphs that capture workflow structure to predict KV cache reuse across tool-call boundaries, achieving within 1.31x of Bélády's optimal offline policy; (2) session-affinity batching with work stealing that co-locates correlated requests while maintaining global load balance; and (3) Agent Fair Share, a task-completion-time fairness metric with provable bounded-deviation guarantees. On a 64-GPU cluster serving SWE-bench coding agents and WebArena browser tasks, SAGA reduces task completion time by 1.64x (geometric mean, p < 0.001) over vLLM v0.15.1 with prefix caching and affinity routing, while improving GPU memory utilization by 1.22x and achieving 99.2% SLO attainment under multi-tenant interference. These latency gains come at a quantified cost: approximately 30% lower peak throughput than throughput-optimal batch scheduling, a tradeoff appropriate for the latency-sensitive interactive deployments that dominate compound AI usage. Our results demonstrate that workflow-aware scheduling is essential for efficient compound AI serving.

Serving Large Language Models (LLMs) is critical for AI-powered applications but demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key technique to improve efficiency while reducing resource consumption. Existing approaches for generating low-precision kernels are limited to weight bit widths that are powers of two and suffer from suboptimal performance due to high-level GPU programming abstractions. These abstractions restrict critical optimizations, such as fine-grained register management and optimized memory access patterns, which are essential for efficient low-precision computations. In this paper, we introduce a virtual machine (VM) designed for General-Purpose GPU (GPGPU) computing, enabling support for low-precision data types with arbitrary bit widths while maintaining GPU programmability. The proposed VM features a thread-block-level programming model, a hierarchical memory space, a novel algebraic layout system, and extensive support for diverse low-precision data types. VM programs are compiled into highly efficient GPU programs with automatic vectorization and instruction selection. Extensive experiments demonstrate that our VM efficiently supports a full spectrum of low-precision data types, and outperforms state-of-the-art low-precision kernels on their supported types. Compared to existing compilers like Triton and Ladder, as well as hand-optimized kernels such as QuantLLM and Marlin, our VM achieves performance improvements of 1.75x, 2.61x, 1.29x and 1.03x, respectively.

Deploying LLMs efficiently requires testing hundreds of serving configurations, but evaluating each one on a GPU cluster takes hours and costs thousands of dollars. Discrete-event simulators are faster and cheaper, but they require re-implementing the serving system's control logic -- a burden that compounds as frameworks evolve. We present Revati, a time-warp emulator that enables performance modeling by directly executing real serving system code at simulation-like speed. The system intercepts CUDA API calls to virtualize device management, allowing serving frameworks to run without physical GPUs. Instead of executing GPU kernels, it performs time jumps -- fast-forwarding virtual time by predicted kernel durations. We propose a coordination protocol that synchronizes these jumps across distributed processes while preserving causality. On vLLM and SGLang, Revati achieves less than 5% prediction error across multiple models and parallelism configurations, while running 5-17x faster than real GPU execution.

On the way to Exascale, programmers face the increasing challenge of having to support multiple hardware architectures from the same code base. At the same time, portability of code and performance are increasingly difficult to achieve as hardware architectures are becoming more and more diverse. Today's heterogeneous systems often include two or more completely distinct and incompatible hardware execution models, such as GPGPU's, SIMD vector units, and general purpose cores which conventionally have to be programmed using separate tool chains representing non-overlapping programming models. The recent revival of interest in the industry and the wider community for the C++ language has spurred a remarkable amount of standardization proposals and technical specifications in the arena of concurrency and parallelism. This recently includes an increasing amount of discussion around the need for a uniform, higher-level abstraction and programming model for parallelism in the C++ standard targeting heterogeneous and distributed computing. Such an abstraction should perfectly blend with existing, already standardized language and library features, but should also be generic enough to support future hardware developments. In this paper, we present the results from developing such a higher-level programming abstraction for parallelism in C++ which aims at enabling code and performance portability over a wide range of architectures and for various types of parallelism. We present and compare performance data obtained from running the well-known STREAM benchmark ported to our higher level C++ abstraction with the corresponding results from running it natively. We show that our abstractions enable performance at least as good as the comparable base-line benchmarks while providing a uniform programming API on all compared target architectures.

Recent studies have demonstrated the potential of Large Language Models (LLMs) in generating GPU Kernels. Current benchmarks focus on the translation of high-level languages into CUDA, overlooking the more general and challenging task of text-to-CUDA generation. Furthermore, given the hardware-specific and performance-critical features of GPU programming, accurately assessing the performance of LLM-generated GPU programs is nontrivial. In this work, we introduce CUDABench, a comprehensive benchmark designed to evaluate the text-to-CUDA capabilities of LLMs. First, we construct CUDABench-Set, which covers Breadth-Depth-Difficulty evaluation space in diverse application domains, including artificial intelligence, scientific computing, and data analytics, etc. Furthermore, we propose CUDABench-Score and Generative Verification Pipeline that assess (1) compilation correctness, (2) functional consistency through execution-based verification, and (3) a novel roofline-based metric, Performance-Score. Benchmarking state-of-the-art LLMs reveals insightful findings and challenges of text-to-CUDA, such as a notable mismatch between high compilation success rates and low functional correctness, a lack of domain-specific algorithmic knowledge, and suboptimal utilization of GPU hardware resources. Our benchmark is available at https://github.com/CUDA-Bench/CUDABench.

Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is very expensive and often hits a ``memory wall'', i.e., even when using 3D parallelism (pipeline, tensor, data) and aggregating the memory of many GPUs, it is still not enough to hold the necessary data structures (model parameters, optimizer state, gradients, activations) in GPU memory. To compensate, state-of-the-art approaches offload the optimizer state, at least partially, to the host memory and perform hybrid CPU-GPU computations. However, the management of the combined host-GPU memory is often suboptimal and results in poor overlapping between data movements and computations. This leads to missed opportunities to simultaneously leverage the interconnect bandwidth and computational capabilities of CPUs and GPUs. In this paper, we leverage a key observation that the interleaving of the forward, backward and update phases generate fluctuations in the GPU memory utilization, which can be exploited to dynamically move a part of the optimizer state between the host and the GPU memory at each iteration. To this end, we design and implement \proj, a novel technique to split the LLM into subgroups, whose update phase is scheduled on either the CPU or the GPU based on our proposed performance model that addresses the trade-off between data movement cost, acceleration on the GPUs vs the CPUs, and competition for shared resources. We integrate our approach with DeepSpeed and demonstrate 2.5times faster iterations over state-of-the-art approaches using extensive experiments.

Meta deploys a heterogeneous fleet comprising NVIDIA GPUs, AMD GPUs, and proprietary MTIA accelerators to reduce costs and mitigate vendor lock-in. However, the extensive history of NVIDIA-specific optimizations hinders performance portability to other hardware. This paper presents our methods for optimizing alternative accelerators, using AMD Instinct MI350X versus NVIDIA B200 for recommendation model training as a case study. We propose three reusable principles. First, hardware-model co-design is essential: rather than directly porting models from NVIDIA GPUs, revising model structures and software recipes allows full exploitation of accelerator-specific strengths (e.g., MI350X's 1.6x HBM capacity relative to B200). Second, our analytical performance model enables zero-warmup optimal kernel selection across diverse datatypes and matrix shapes in production models, drastically simplifying tuning. Third, increasingly mature agentic workflows have lowered the barrier to porting from the CUDA ecosystem; we extend these workflows for microarchitecture-aware kernel optimizations and custom shim generation. Compared to the directly ported baseline, these methods deliver up to 1.5x improvement in end-to-end training throughput. To our knowledge, this is the first hyperscaler report on productionizing AMD GPUs for large-scale training. Our contributions have been upstreamed to the open-source PyTorch, Triton, and ROCm ecosystems.

GPU-initiated communication lets GPU threads post RDMA operations directly to the NIC. It underpins NVSHMEM, NCCL GIN, and DeepEP, which serve the fine-grained, latency-critical communication of Mixture-of-Experts (MoE) models, yet its performance characteristics and optimizations remain scarcely documented beyond source code, and library comparisons fail to separate the costs of the hardware mechanism from those of the library around it. This paper dissects GPU-initiated communication at the GPU-NIC boundary. We first detail the GPU-side network path: queue placement, work-request construction, doorbell ordering, and completion semantics. We then introduce mini-gda and mini-proxy, minimal transports for the GPU and CPU-proxy submission paths, and measure them alongside NVSHMEM IBGDA, NCCL GIN, DeepEP, UCCL-EP, MSCCL++, and fabric-lib on NVIDIA H100, H200, B200, and GB200 platforms. A minimal GPU path issues an operation in 0.7 μs and completes in 4.0 μs; libraries add up to 4.6 μs of issue time through queue management, memory ordering, and completion scope, and issue time scales with the SM clock. A tuned CPU proxy matches or beats the GPU path at idle, at the cost of a dedicated core whose operating state sets its latency and throughput. On either path, sharing a queue with bulk traffic raises latency by one to three orders of magnitude. Reaching the 260 M msg/s ceiling of our InfiniBand platform requires doorbell batching and queue parallelism, and both have resource costs: communication code can reduce GPU block residency even when unused, and all-to-all traffic loses 59% of its NIC message rate at about 3,000 active connections. The submission path alone therefore does not predict communication performance. Our experiment code and results are available at https://github.com/ParCoreLab/Dissecting-GPU-Communication-Experiments.

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their inference efficiency remains a critical bottleneck due to rapidly growing parameters. Recent advances in dynamic computation allocation address this challenge by exploiting the highly uneven contributions of different tokens and layers, enabling selective execution that significantly reduces redundant computation while preserving model accuracy. However, existing hardware platforms and accelerators are primarily optimized for uniform, static execution, limiting their ability to efficiently support such dynamic inference patterns. In this work, we propose SkipOPU, an FPGA-based overlay processor that dynamically allocates computation across tokens and layers with high flexibility through a lightweight routing mechanism. First, we decouple reduction operations from element-wise computation in nonlinear modules and perform reductions incrementally, which enables both stages to be fused with adjacent linear operations (router or matrix multiplication) for effective latency hiding. Second, motivated by asymmetric sensitivity to numerical precision between activation and weight, we design a PE array that efficiently supports float-fixed hybrid execution. A novel DSP overpacking technique is introduced to maximize hardware utilization while minimizing resource overhead. Finally, we develop a proactive on-chip KV history buffer that exploits cross-layer KV invariance of pruned tokens, eliminating irregular HBM accesses during decoding and supplementing off-chip bandwidth through high-locality on-chip reuse. Experimental results demonstrate that SkipOPU on an AMD U280 FPGA outperforms GPU and other FPGA-based accelerators by 1.23x-3.83x in bandwidth efficiency for LLMs inference with dynamic computation allocation and can reduce up to 25.4% KV storage overhead across varying sequence lengths.

The challenge of mapping AI architectures to GPU hardware is creating a critical bottleneck in AI progress. Despite substantial efforts, hand-written custom kernels fail to meet their theoretical performance thresholds, even on well-established operations like linear attention. The diverse hardware capabilities of GPUs might suggest that we need a wide variety of techniques to achieve high performance. However, our work explores whether a small number of key abstractions can drastically simplify the process. We present ThunderKittens (TK), a framework for writing performant AI kernels while remaining easy to use and maintain. Our abstractions map to the three levels of the GPU hierarchy: (1) at the warp-level, we provide 16x16 matrix tiles as basic data structures and PyTorch-like parallel compute operations over tiles, (2) at the thread-block level, we provide a template for overlapping asynchronous operations across parallel warps, and (3) at the grid-level, we provide support to help hide the block launch and tear-down, and memory costs. We show the value of TK by providing kernels that match or outperform prior kernels for a range of AI operations. We match CuBLAS and FlashAttention-3 on GEMM and attention inference performance and outperform the strongest baselines by 10-40% on attention backwards, 8times on state space models, and 14times on linear attention.

Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination. While some predictive models exist, they still require profiling data and struggle to generalize to hardware unseen during training. To address this, we introduce WattGPU, featuring two predictive models for mean GPU power draw and Inter-Token Latency (ITL). Our approach leverages only publicly available LLM metadata and GPU specifications, eliminating the need for hardware access or profiling while enabling generalization to unseen NVIDIA server-grade GPUs and LLMs. We evaluate our models using rigorous leave-one-GPU-out and leave-one-LLM-out cross-validation on a dataset of 42 open-source LLMs (0.1B--27B parameters) and 8 GPUs under both offline and server scenarios. The mean power draw model achieves a median absolute percentage error of leq3.4% for offline and leq13.5% for server scenarios on unseen GPUs, while the latency model achieves leq8.5% in server mode, both maintaining strong GPU ranking correlations for server scenarios (Kendall τgeq0.76). Compared to standard physically grounded baselines -- Load-Scaled Thermal Design Power (TDP) for power draw and roofline for latency -- our models reduce median absolute percentage error by approximately 4times on unseen LLM-GPU combinations for server scenarios or approximately 2times for completely unseen GPUs. WattGPU's data and code are publicly available at https://github.com/maufadel/wattgpu.

The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely generalizable GPU performance models to support next-generation hardware selection and system-level exploration. However, current data-driven methods are limited, exhibiting poor generalization across hardware and inadequate modeling of complex production-level kernels common in modern inference stacks. To address these issues, we present PipeWeave, a unified GPU modeling framework. This approach first employs an analytical model to quantify a given kernel's demands on the GPU's heterogeneous instruction pipelines. These analytical features are then fed into a machine learning (ML) model to capture complex cross-pipeline interactions and resource dependencies, enabling high-fidelity performance prediction. Our evaluation across 11 GPU types from four generations of major architectures on two widely-used serving systems demonstrates that PipeWeave delivers high fidelity and strong generalizability. It achieves accurate predictions, with only 6.1% average error at the kernel level and 8.5% for end-to-end inference -- reducing the error of state-of-the-art methods by 6.7x and 4.4x, respectively. We also demonstrate PipeWeave's value "beyond simulation" by utilizing its performance ceiling to diagnose implementation shortcomings and guide the optimization of a production fused MoE Triton kernel, achieving up to 1.7x speedup. Code is available https://github.com/zksainx/pipeweave.

Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively parallel GPUs, remains a complex challenge. In this work, we explore the use of LLMs for the automated generation and optimization of CUDA programs, with the goal of producing high-performance GPU kernels that fully exploit the underlying hardware. To address this challenge, we propose a novel framework called Feature Search and Reinforcement (FSR). FSR jointly optimizes compilation and functional correctness, as well as the runtime performance, which are validated through extensive and diverse test cases, and measured by actual kernel execution latency on the target GPU, respectively. This approach enables LLMs not only to generate syntactically and semantically correct CUDA code but also to iteratively refine it for efficiency, tailored to the characteristics of the GPU architecture. We evaluate FSR on representative CUDA kernels, covering AI workloads and computational intensive algorithms. Our results show that LLMs augmented with FSR consistently guarantee correctness rates. Meanwhile, the automatically generated kernels can outperform general human-written code by a factor of up to 179times in execution speeds. These findings highlight the potential of combining LLMs with performance reinforcement to automate GPU programming for hardware-specific, architecture-sensitive, and performance-critical applications.

While accelerated computing has transformed many domains of computing, its impact on logical reasoning, specifically Boolean satisfiability (SAT), remains limited. State-of-the-art SAT solvers rely heavily on inherently sequential conflict-driven search algorithms that offer powerful heuristics but limit the amount of parallelism that could otherwise enable significantly more scalable SAT solving. Inspired by neural network training, we formulate the SAT problem as a binarized matrix-matrix multiplication layer that could be optimized using a differentiable objective function. Enabled by this encoding, we combine the strengths of parallel differentiable optimization and sequential search to accelerate SAT on a hybrid GPU-CPU system. In this system, the GPUs leverage parallel differentiable solving to rapidly evaluate SAT clauses and use gradients to stochastically explore the solution space and optimize variable assignments. Promising partial assignments generated by the GPUs are post-processed on many CPU threads which exploit conflict-driven sequential search to further traverse the solution subspaces and identify complete assignments. Prototyping the hybrid solver on an NVIDIA DGX GB200 node, our solver achieves runtime speedups up to over 200x when compared to a state-of-the-art CPU-based solver on public satisfiable benchmark problems from the SAT Competition.

LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.

The exponential growth in demand for GPU computing resources, driven by the rapid advancement of Large Language Models, has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models (e.g. R1, o1) achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization. CUDA-L1 achieves performance improvements on the CUDA optimization task: trained on NVIDIA A100, it delivers an average speedup of x17.7 across all 250 CUDA kernels of KernelBench, with peak speedups reaching x449. Furthermore, the model also demonstrates excellent portability across GPU architectures, achieving average speedups of x17.8 on H100, x19.0 on RTX 3090, x16.5 on L40, x14.7 on H800, and x13.9 on H20 despite being optimized specifically for A100. Beyond these benchmark results, CUDA-L1 demonstrates several remarkable properties: 1) Discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) Uncovers fundamental principles of CUDA optimization; 3) Identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that harm performance. The capabilities of CUDA-L1 demonstrate that reinforcement learning can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. More importantly, the trained RL model extend the acquired reasoning abilities to new kernels. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.

Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize functionally correct CUDA code, achieving competitive performance requires systematic exploration and verification of optimization choices. We present OptiML, an end-to-end framework that maps either natural-language intent or input CUDA code to performance-optimized CUDA kernels by formulating kernel optimization as search under verification. OptiML consists of two decoupled stages. When the input is natural language, a Mixture-of-Thoughts generator (OptiML-G) acts as a proposal policy over kernel implementation strategies, producing an initial executable program. A search-based optimizer (OptiML-X) then refines either synthesized or user-provided kernels using Monte Carlo Tree Search over LLM-driven edits, guided by a hardware-aware reward derived from profiler feedback. Each candidate transformation is compiled, verified, and profiled with Nsight Compute, and evaluated by a composite objective that combines runtime with hardware bottleneck proxies and guardrails against regressions. We evaluate OptiML in both synthesis-and-optimize and optimization-only settings on a diverse suite of CUDA kernels. Results show that OptiML consistently discovers verified performance improvements over strong LLM baselines and produces interpretable optimization trajectories grounded in profiler evidence.

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a benchmark that evaluates generated CUDA against end-to-end human-expert SOTA systems. It spans single kernels, module-level operators, full applications, and unsolved challenge tasks across Ampere, Hopper, and Blackwell GPUs, with end-to-end tasks gated by domain-specific semantic validators. Evaluating models such as Claude-Opus-4.6 and GPT-5.4 shows a large gap between runnable CUDA and expert CUDA engineering: models often compile and pass tests, but rarely recover the optimization strategies needed to match expert performance. Application semantics further reduce success, and iterative or tool-augmented feedback can improve correctness while drifting toward slow fallback implementations. These results show that automated CUDA programming remains far from fully solved and requires stronger hardware reasoning, better tool use, and training objectives that connect code understanding to hardware architecture-grounded intelligence.

Optimizing GPU kernels manually is a challenging and time-consuming task. With the rapid development of LLMs, automated GPU kernel optimization is gradually becoming a tangible reality. However, current LLM-driven automated optimization methods narrowly focus on machine learning applications, such as PyTorch operator optimization, while overlooking broader domains like sparse matrix operations in scientific computing. Extending to these broader applications brings new challenges for the benchmark and algorithm. Therefore, developing a general-purpose automated kernel optimization method becomes our primary focus. In this paper, we address the absence of systematic evaluation for multi-scenario settings by introducing MSKernelBench, which spans multiple scenarios, including fundamental algebraic operations, common LLM kernels, sparse matrix operators, and scientific computing routines, each supporting both FP32 and BF16 precision. Building on this benchmark, we introduce CUDAMaster, a multi-agent, hardware-aware system for kernel optimization that leverages profiling information and automatically constructs the full compilation and execution toolchain. Experimental results demonstrate that CUDAMaster achieves significant speedups across most operators, outperforming Astra by about 35%. In several cases, its performance matches or surpasses that of highly optimized, closed-source libraries such as cuBLAS. A demo showcasing the original and optimized code for each operator is available at https://hanyx2021.github.io/MSKernelBenchDemo/.

Graphics processing units (GPUs) are continually evolving to cater to the computational demands of contemporary general-purpose workloads, particularly those driven by artificial intelligence (AI) utilizing deep learning techniques. A substantial body of studies have been dedicated to dissecting the microarchitectural metrics characterizing diverse GPU generations, which helps researchers understand the hardware details and leverage them to optimize the GPU programs. However, the latest Hopper GPUs present a set of novel attributes, including new tensor cores supporting FP8, DPX, and distributed shared memory. Their details still remain mysterious in terms of performance and operational characteristics. In this research, we propose an extensive benchmarking study focused on the Hopper GPU. The objective is to unveil its microarchitectural intricacies through an examination of the new instruction-set architecture (ISA) of Nvidia GPUs and the utilization of new CUDA APIs. Our approach involves two main aspects. Firstly, we conduct conventional latency and throughput comparison benchmarks across the three most recent GPU architectures, namely Hopper, Ada, and Ampere. Secondly, we delve into a comprehensive discussion and benchmarking of the latest Hopper features, encompassing the Hopper DPX dynamic programming (DP) instruction set, distributed shared memory, and the availability of FP8 tensor cores. The microbenchmarking results we present offer a deeper understanding of the novel GPU AI function units and programming features introduced by the Hopper architecture. This newfound understanding is expected to greatly facilitate software optimization and modeling efforts for GPU architectures. To the best of our knowledge, this study makes the first attempt to demystify the tensor core performance and programming instruction sets unique to Hopper GPUs.

GPU architectures have continued to grow in complexity, with recent incarnations introducing increasingly powerful fixed-function units for matrix multiplication and data movement to accompany highly parallel general-purpose cores. To fully leverage these machines, software must use sophisticated schedules that maximally utilize all hardware resources. Since realizing such schedules is complex, both programmers and compilers routinely employ program transformations, such as software pipelining (SWP) and warp specialization (WS), to do so in practice. However, determining how best to use SWP and WS in combination is a challenging problem that is currently handled through a mix of brittle compilation heuristics and fallible human intuition, with little insight into the space of solutions. To remedy this situation, we introduce a novel formulation of SWP and WS as a joint optimization problem that can be solved holistically by off-the-shelf constraint solvers. We reify our approach in Twill, the first system that automatically derives optimal SWP and WS schedules for a large class of iterative programs. Twill is heuristic-free, easily extensible to new GPU architectures, and guaranteed to produce optimal schedules. We show that Twill can rediscover, and thereby prove optimal, the SWP and WS schedules manually developed by experts for Flash Attention on both the NVIDIA Hopper and Blackwell GPU architectures.

Fine-tuning large language models (LLMs) often exceeds GPU memory limits, prompting systems to offload model states to CPU memory. However, existing offloaded training frameworks like ZeRO-Offload treat all parameters equally and update the full model on the CPU, causing severe GPU stalls, where fast, expensive GPUs sit idle waiting for slow CPU updates and limited-bandwidth PCIe transfers. We present ZenFlow, a new offloading framework that prioritizes important parameters and decouples updates between GPU and CPU. ZenFlow performs in-place updates of important gradients on GPU, while asynchronously offloading and accumulating less important ones on CPU, fully overlapping CPU work with GPU computation. To scale across GPUs, ZenFlow introduces a lightweight gradient selection method that exploits a novel spatial and temporal locality property of important gradients, avoiding costly global synchronization. ZenFlow achieves up to 5x end-to-end speedup, 2x lower PCIe traffic, and reduces GPU stalls by over 85 percent, all while preserving accuracy.

As agentic AI systems become increasingly capable of generating and optimizing GPU kernels, progress is constrained by benchmarks that reward speedup over software baselines rather than proximity to hardware-efficient execution. We present SOL-ExecBench, a benchmark of 235 CUDA kernel optimization problems extracted from 124 production and emerging AI models spanning language, diffusion, vision, audio, video, and hybrid architectures, targeting NVIDIA Blackwell GPUs. The benchmark covers forward and backward workloads across BF16, FP8, and NVFP4, including kernels whose best performance is expected to rely on Blackwell-specific capabilities. Unlike prior benchmarks that evaluate kernels primarily relative to software implementations, SOL-ExecBench measures performance against analytically derived Speed-of-Light (SOL) bounds computed by SOLAR, our pipeline for deriving hardware-grounded SOL bounds, yielding a fixed target for hardware-efficient optimization. We report a SOL Score that quantifies how much of the gap between a release-defined scoring baseline and the hardware SOL bound a candidate kernel closes. To support robust evaluation of agentic optimizers, we additionally provide a sandboxed harness with GPU clock locking, L2 cache clearing, isolated subprocess execution, and static analysis based checks against common reward-hacking strategies. SOL-ExecBench reframes GPU kernel benchmarking from beating a mutable software baseline to closing the remaining gap to hardware Speed-of-Light.

The AIPC concept is gaining popularity, and more and more hybrid CPUs will be running AI models on client devices. However, the current AI inference framework overlooks the imbalanced hardware capability of hybrid CPUs, leading to low inference performance. To address this issue, we have introduced a dynamic parallel method for hybrid CPUs, which significantly increases LLM inference performance by balancing the workload for each core of a hybrid CPU before the parallel work starts. This method has enabled Neural Speed to achieve more than 90% (on average) of memory bandwidth on two hybrid Intel CPUs.

The increasing usage of Large Language Models (LLMs) has resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput (under reasonable latency constraints) has emerged as a key metric that determines serving systems' performance. To boost throughput, various methods of inter-device parallelism (e.g., data, tensor, pipeline) have been explored. However, existing methods do not consider overlapping the utilization of different resources within a single device, leading to underutilization and sub-optimal performance. We propose NanoFlow, a novel serving framework that exploits intra-device parallelism, which overlaps the usage of resources including compute, memory, and network within a single device through operation co-scheduling. To exploit intra-device parallelism, NanoFlow introduces two key innovations: First, NanoFlow splits requests into nano-batches at the granularity of operations, which breaks the dependency of sequential operations in LLM inference and enables overlapping; then, to get benefit from overlapping, NanoFlow uses an operation-level pipeline with execution unit scheduling, which partitions the device's functional units and simultaneously executes different operations in each unit. NanoFlow automates the pipeline setup using a parameter search algorithm, which enables easily porting NanoFlow to different models. We implement NanoFlow on NVIDIA GPUs and evaluate end-to-end serving throughput on several popular models such as LLaMA-2-70B, Mixtral 8x7B, LLaMA-3-8B, etc.. With practical workloads, NanoFlow provides 1.91x throughput boost compared to state-of-the-art serving systems achieving 59% to 72% of optimal throughput across ported models.

Heterogeneous CPU-GPU workloads are increasingly used in safety-critical embedded systems, yet no existing approach provides joint attestation of their execution. Prior Control-Flow Attestation (CFA) techniques focus on CPU-side CFA, while GPU attestation is limited to static, load-time verification and does not provide runtime guarantees. As a result, runtime attacks on GPU kernels and violations of the CPU-GPU interaction contract remain unaddressed. We present WarpGuard, the first composite CFA framework for heterogeneous CPU-GPU workloads. WarpGuard verifies execution against a unified control-flow graph (CFG) that captures both CPU and GPU components. It extends prior CFA techniques in two ways: it enables runtime CFA of GPU kernels by tracing their execution against kernel-specific CFGs, and it monitors kernel launch events and enforces per-call site policies to detect violations at the CPU-GPU boundary. These extensions address challenges arising from GPU parallelism and cross-device interactions. We implement WarpGuard using software-based instrumentation, requiring no specialized hardware or binary modifications. Our evaluation on an NVIDIA Jetson Orin Nano shows that WarpGuard detects GPU-side control-flow and cross-boundary attacks. Across microbenchmarks, SPECAccel, and eight TensorRT inference workloads, WarpGuard incurs moderate overheads, suggesting practicality for embedded safety-critical settings.

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path. This paradigm has greatly improved training speed, but it has also encouraged a default assumption that efficient training requires physics to reside on the GPU. We revisit this assumption. Our view is that, in simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop. We present UniLab, a heterogeneous CPU-simulation / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization. UniLab is implemented as a complete and extensible training system using MuJoCoUni and MotrixSim CPU-batched physics backends, supporting PPO, FastSAC, FlashSAC, and APPO. On representative simulation-based robot control tasks, UniLab improves end-to-end training efficiency by 3--10times under the same hardware configuration, while reducing dependence on the NVIDIA CUDA-based software stack and supporting cross-platform execution on the Apple macOS platform and the AMD ROCm and Intel XPU accelerator backends. These results show that GPU simulation is an effective path to efficient training, but not a necessary one, broadening the practical system choices available for robot RL training. Project page: https://unilabsim.github.io.

Explicit graphics APIs expose memory dependencies, per-resource accesses, and image layouts. wgpu reconstructs and validates this state; Blade keeps Vulkan images in GENERAL, tracks no per-resource state, and issues global pass-boundary barriers. We isolate barrier placement and stage/access scope within Blade, compare matched wgpu programs end-to-end, and measure six GPUs from four vendors, including exploratory Apple/Metal results. Removing fifteen redundant barriers from sixteen independent compute passes reduces GPU span by 29.3% on an RTX 5070 and 32.3% on an RX 7900 XT. It reduces independent-render span by 32.4% and 7.3% on the same discrete parts, but increases Radeon 780M span by 42.4% at 32 passes, beyond a 12.3% count-specific stability floor. No dependent-chain placement effect clears the study's cell-specific stability criterion. Deriving global barrier scope from the pass kinds around each boundary, without tracking any resource, saves 5.0% on an NVIDIA graphics chain and 6.7% on an AMD compute chain; no AMD render-involving scope cell resolves. wgpu's record-and-submit cost is higher in every measured cell, but this end-to-end difference cannot be attributed to tracking alone. RADV source shows why command counts do not predict these costs: broad global dependencies expand to several flush and invalidate requests that the driver may partly elide. It also shows that persistent GENERAL retains DCC under the measured RDNA conditions but disables FMASK. The resulting Blade direction is lightweight aggregate pass-kind state in a tracking-free RHI: an upstream render graph selects global dependency cuts, while aliasing, cross-queue use, exceptional layouts, and arbitrary per-resource DAG edges remain resource-aware engine responsibilities.

With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI agents, and video generation, contemporary mobile systems have begun integrating these AI capabilities on local devices to enhance privacy and reduce response latency. To meet the computational demands of AI tasks, current mobile SoCs are equipped with diverse AI accelerators, including GPUs and Neural Processing Units (NPUs). However, there has not been a comprehensive characterization of these heterogeneous processors, and existing designs typically only leverage a single AI accelerator for LLM inference, leading to suboptimal use of computational resources and memory bandwidth. In this paper, we first summarize key performance characteristics of heterogeneous processors, SoC memory bandwidth, etc. Drawing on these observations, we propose different heterogeneous parallel mechanisms to fully exploit both GPU and NPU computational power and memory bandwidth. We further design a fast synchronization mechanism between heterogeneous processors that leverages the unified memory architecture. By employing these techniques, we present HeteroInfer, the fastest LLM inference engine in mobile devices which supports GPU-NPU heterogeneous execution. Evaluation shows that HeteroInfer delivers a 1.34x to 6.02x end-to-end speedup over state-of-the-art GPU-only and NPU-only LLM engines, while maintaining negligible interference with other applications.

We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance megakernel. MPK introduces an SM-level graph representation that captures data dependencies at the granularity of individual streaming multiprocessors (SMs), enabling cross-operator software pipelining, fine-grained kernel overlap, and other previously infeasible GPU optimizations. The MPK compiler lowers tensor programs into highly optimized SM-level task graphs and generates optimized CUDA implementations for all tasks, while the MPK in-kernel parallel runtime executes these tasks within a single mega-kernel using decentralized scheduling across SMs. Together, these components provide end-to-end kernel fusion with minimal developer effort, while preserving the flexibility of existing programming models. Our evaluation shows that MPK significantly outperforms existing kernel-per-operator LLM serving systems by reducing end-to-end inference latency by up to 1.7x, pushing LLM inference performance close to hardware limits. MPK is publicly available at https://github.com/mirage-project/mirage.

Training and deployed inference often cross export, conversion, and platform-specific runtime boundaries. Meganeura asks whether one compact native compiler can span both phases on consumer GPUs. Its typed static graph, automatic differentiation, optimizer, checkpoint, memory planner, and runtime lower specialized programs through Vulkan and Metal. We compare five matched workloads with PyTorch on NVIDIA and AMD discrete GPUs, an AMD APU, Apple silicon, and an Intel iGPU. The protocol separates strict f32 from validated fast paths and gates forward and backward independently. Forty-eight of 50 device-workload-mode cells pass both gates; the other two share one unresolved backward-reference disagreement on a newly supported APU. In strict f32, Meganeura wins 12 of 20 GPU-referenced minimal-latency cells and has a median valid training gap of 1.8x. On the discrete AMD GPU, four of five inference workloads are within 1.10x of compiled ROCm PyTorch and three training workloads are faster. Under accelerated contracts, the worst training gap is 4.6x. Compilation takes 0.1-2.4 seconds versus 6-96 seconds for torch.compile on supported GPU paths; the stripped binary is 13 MiB. Dispatch profiles localize the largest gaps to convolution derivatives and attention backward. A physical Android XR case study transfers a Meganeura-trained decoder into an Adreno/OpenXR application sharing the graphics queue. The results show that general consumer graphics APIs can support a compact shared train-to-deploy stack at useful, sometimes vendor-competitive performance. The measured gaps point to kernel coverage, scheduling, and arithmetic policy rather than an identified API limitation.

Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the utilization of GPUs as much as possible. However, those specialized kernels may still leave performance on the table as CUDA assembly experts show that manual optimization of GPU SASS schedules can lead to better performance, and trial-and-error is largely employed to manually find the best GPU SASS schedules. In this work, we employ an automatic approach to optimize GPU SASS schedules, which thus can be integrated into existing compiler frameworks. The key to automatic optimization is training an RL agent to mimic how human experts perform manual scheduling. To this end, we formulate an assembly game, where RL agents can play to find the best GPU SASS schedules. The assembly game starts from a -O3 optimized SASS schedule, and the RL agents can iteratively apply actions to mutate the current schedules. Positive rewards are generated if the mutated schedules get higher throughput by executing on GPUs. Experiments show that CuAsmRL can further improve the performance of existing specialized CUDA kernels transparently by up to 26%, and on average 9%. Moreover, it is used as a tool to reveal potential optimization moves learned automatically.

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM workloads due to rigid execution models and specialization for dense matrix operations. This paper proposes architectural extensions to a baseline Reconfigurable Dataflow Unit (RDU) that efficiently support FFT-based and scan-based SSMs. By introducing lightweight interconnect enhancements within compute tiles, the extended RDU enables spatial mapping of FFT and scan dataflows with less than 1% area and power overhead. The resulting architecture achieves a 5.95X speedup over the GPU and a 1.95X speedup over the baseline RDU for Hyena, and a 2.12X and 1.75X speedup over the GPU and baseline RDU, respectively, for Mamba.

Large language models (LLMs) are increasingly integrated into many online services. However, a major challenge in deploying LLMs is their high cost, due primarily to the use of expensive GPU instances. To address this problem, we find that the significant heterogeneity of GPU types presents an opportunity to increase GPU cost efficiency and reduce deployment costs. The broad and growing market of GPUs creates a diverse option space with varying costs and hardware specifications. Within this space, we show that there is not a linear relationship between GPU cost and performance, and identify three key LLM service characteristics that significantly affect which GPU type is the most cost effective: model request size, request rate, and latency service-level objective (SLO). We then present M\'elange, a framework for navigating the diversity of GPUs and LLM service specifications to derive the most cost-efficient set of GPUs for a given LLM service. We frame the task of GPU selection as a cost-aware bin-packing problem, where GPUs are bins with a capacity and cost, and items are request slices defined by a request size and rate. Upon solution, M\'elange derives the minimal-cost GPU allocation that adheres to a configurable latency SLO. Our evaluations across both real-world and synthetic datasets demonstrate that M\'elange can reduce deployment costs by up to 77% as compared to utilizing only a single GPU type, highlighting the importance of making heterogeneity-aware GPU provisioning decisions for LLM serving. Our source code is publicly available at https://github.com/tyler-griggs/melange-release.

GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that produces and iteratively refines programs through compilation and correctness feedback, and a performance analysis agent that interprets profiling data to guide optimization. This agent-based architecture requires only a single-shot example to target new platforms. We make three key contributions: (1) introducing an iterative refinement system where the generation agent and performance analysis agent collaborate through functional and optimization passes, interpreting diverse profiling data (from programmatic APIs to GUI-based tools) to generate actionable recommendations that guide program synthesis for arbitrary accelerators; (2) demonstrating that the generation agent effectively leverages cross-platform knowledge transfer, where a reference implementation from one architecture substantially improves generation quality for different hardware targets; and (3) validating the platform-agnostic nature of our approach by demonstrating effective program synthesis across fundamentally different parallel computing platforms: NVIDIA CUDA and Apple Metal.

Hybrid AI-HPC workflows combine large-scale simulation, training, high-throughput inference, and tightly coupled, agent-driven control within a single execution campaign. These workflows impose heterogeneous and often conflicting requirements on runtime systems, spanning MPI executables, persistent AI services, fine-grained tasks, and low-latency AI-HPC coupling. Existing systems typically address only subsets of these requirements, limiting their ability to support emerging AI-HPC applications at scale. We present RHAPSODY, a multi-runtime middleware that enables concurrent execution of heterogeneous AI-HPC workloads through uniform abstractions for tasks, services, resources, and execution policies. Rather than replacing existing runtimes, RHAPSODY composes and coordinates them, allowing simulation codes, inference services, and agentic workflows to coexist within a single job allocation on leadership-class HPC platforms. We evaluate RHAPSODY with Dragon and vLLM on multiple HPC systems using representative heterogeneous, inference-at-scale, and tightly coupled AI-HPC workflows. Our results show that RHAPSODY introduces minimal runtime overhead, sustains increasing heterogeneity at scale, achieves near-linear scaling for high-throughput inference workloads, and data- and control-efficient coupling between AI and HPC tasks in agentic workflows.

Parallel programming is central to HPC and AI, but producing code that is correct and fast remains challenging, especially for OpenMP GPU offload, where data movement and tuning dominate. Autonomous coding agents can compile, test, and profile on target hardware, but outputs are brittle without domain scaffolding. We present ParaCodex, an HPC-engineer workflow that turns a Codex-based agent into an autonomous OpenMP GPU offload system using staged hotspot analysis, explicit data planning, correctness gating, and profiling-guided refinement. We evaluate translation from serial CPU kernels to OpenMP GPU offload kernels on HeCBench, Rodinia, and NAS. After excluding five kernels, ParaCodex succeeded on all 31 valid kernels. The generated kernels improved GPU time over reference OpenMP implementations in 25/31 cases, achieving geometric-mean speedups of 3x on HeCBench and 5x on Rodinia, and outperforming a zero-shot Codex baseline on all suites. We also evaluate CUDA to OpenMP offload translation on ParEval, where ParaCodex maintains high compilation and validation rates in code-only and end-to-end settings.

Rust has made safe systems programming practical on the CPU, but writing custom GPU kernels in Rust still forces programmers outside the language's ownership guarantees. We present cuTile Rust, a tile-based system for safe, idiomatic GPU kernel authoring in Rust. cuTile Rust extends Rust's ownership discipline to tile-based GPU kernels: mutable outputs are split into disjoint pieces, kernel launches preserve the host-side ownership contract, and programmers can opt out locally when they need lower-level control. The system also provides a composable host execution model spanning synchronous launches, asynchronous pipelines, and CUDA graph replay. Our evaluation shows that these abstractions can preserve performance on high-end GPUs. On the NVIDIA B200 GPU, cuTile Rust achieves 7 TB/s for element-wise operations and 2 PFlop/s for GEMM (96% of cuBLAS), matching cuTile Python within measurement noise. Grout, a cuTile-Rust-based inference engine, exercises cuTile Rust across an end-to-end Qwen3 inference path. In batch-1 decode, Grout reaches 171 generated tokens/s for Qwen3-4B on the NVIDIA GeForce RTX 5090 and 82 generated tokens/s for Qwen3-32B on the B200, competitive with vLLM and SGLang and consistent with an HBM roofline sanity check.

GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel benchmarks focus on machine learning operators, leaving irregular, heterogeneous, data-movement-heavy database-style operators untested. We introduce DataKernelBench, which translates SQL into validated PyTorch TorchPlan programs and evaluates LLMs that optimize either the core tensor-bounded snippet or the full query in CUDA or Triton through execution-guided repair. Across ten proprietary and open-weight models on TPC-H SF10 with an H100 GPU, the strongest full-query CUDA configuration achieves 2.11times speedup over torch.compile at full pass rate. We find that higher-performing implementations commonly use kernel fusion and execution-strategy changes, stronger models benefit most from full-query specialization, and workload context matters more than hardware context. To handle data larger than GPU memory, we extend TorchPlan with Dask-cuDF for on-demand partition loading on TPC-H SF100 with four H100 GPUs, achieving 2.54times speedup

The field of plasma physics heavily relies on simulations to model various phenomena, such as instabilities, turbulence, and nonlinear behaviors that would otherwise be difficult to study from a purely theoretical approach. Simulations are fundamental in accurately setting up experiments, which can be extremely costly and complex. As high-fidelity tools, gyrokinetic simulations play a crucial role in discovering new physics, interpreting experimental results, and improving the design of next-generation devices. However, their high computational costs necessitate the use of acceleration platforms to reduce execution time. This work revolves around the TRIangular MEsh based Gyrokinetic (TRIMEG) code, which performs high-accuracy particle-in-cell plasma simulations in tokamak geometries, leveraging a novel finite element approach. The rise of graphical processing units (GPUs) constitutes an occasion to satisfy such computational needs, by offloading the most expensive portion of the code to the accelerators. The chosen approach features GPU offloading with the OpenMP API, which grants portability of the code to different architectures, namely AMD and NVIDIA. The particle pushing as well as the grid-to-particle operations have been ported to GPU platforms. Compiler limitations had to be overcome, and portions of the code were restructured to be suitable for GPU acceleration. Kernel performance was evaluated by carrying out GPU grid size exploration, as well as scalability studies. In addition, the efficiency of hybrid MPI-OpenMP offloading parallelization was assessed. The speedup of the GPU implementation was calculated by comparing it with the pure CPU version using different rationales. The Ion Temperature Gradient (ITG) mode was simulated using the GPU-accelerated version, and its correctness was verified in terms of the energy growth rate and the two-dimensional mode structures.

The emergence of Superchips represents a significant advancement in next-generation AI hardware. These Superchips employ a tightly coupled heterogeneous architecture that integrates GPU and CPU on the same package, which offers unprecedented computational power. However, there has been scant research investigating how LLM training benefits from this new architecture. In this work, for the first time, we study LLM training solutions based on offloading for Superchips. We observe important differences between Superchips and traditional loosely-coupled GPU-CPU architecture, which necessitate revisiting prevailing assumptions about offloading. Based on that, we present SuperOffload, a Superchip-centric offloading system that simultaneously uses Hopper GPU, Grace CPU, and NVLink-C2C interconnect more efficiently. SuperOffload accomplishes this via a combination of techniques, such as adaptive weight offloading, bucketization repartitioning, Superchip-aware casting, speculative execution, and a highly optimized Adam optimizer for Grace CPUs. Our evaluation of SuperOffload on NVIDIA GH200 demonstrates up to 2.5x throughput improvement compared to state-of-the-art offloading-based systems, enabling training of up to 25B model on a single Superchip while achieving high training throughput. We also extend SuperOffload with ZeRO-style data parallelism and DeepSpeed-Ulysses sequence parallelism, enabling training of 13B model with sequence lengths up to 1 million tokens on 8 GH200 while achieving 55% MFU.

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Network (FFN) weights and reading long KV caches. While Tensor Parallelism (TP) helps mitigate the cost of FFN weight reads, it does not scale well for attention. When TP width exceeds the number of KV heads, it leads to inefficient KV duplication, limits parallelism, and constrains batch size. Simultaneously, DRAM reads for long KV histories scale linearly with batch size, further capping efficiency. We introduce Helix Parallelism, a hybrid execution strategy that applies KV parallelism during attention to shard KV caches across GPUs, then reuses the same GPUs for TP in dense LLMs or TPxExpert Parallel (EP) in MoEs during FFN computation. To preserve exact attention behavior, Helix includes a lightweight communication step. To minimize the exposed communication cost, we introduce Helix HOP-B. Helix HOP-B effectively minimizes communication overhead through batchwise overlap, preserving low TTL while improving GPU efficiency. Compared to conventional parallelism approaches, Helix reduces TTL by up to 1.5x at fixed batch sizes and supports up to 32x larger batches under the same latency budget for DeepSeek-R1, pushing forward the throughput-latency Pareto on Blackwell and making real-time inference with ultra-long-sequence practical.

The recent shift in Generative AI (GenAI) applications from cloud-only environments to end-user devices introduces new challenges in resource management, system efficiency, and user experience. This paper presents ConsumerBench, a comprehensive benchmarking framework designed to evaluate the system efficiency and response time of GenAI models running on end-user devices. Unlike existing benchmarks that assume exclusive model access on dedicated GPUs, ConsumerBench simulates realistic multi-application scenarios executing concurrently on constrained hardware. Furthermore, ConsumerBench supports customizable workflows that simulate complex tasks requiring coordination among multiple applications. ConsumerBench captures both application-level metrics, including latency and Service Level Objective (SLO) attainment, and system-level metrics like CPU/GPU utilization and memory bandwidth. Through extensive experiments, ConsumerBench reveals inefficiencies in resource sharing, unfair scheduling under greedy allocation, and performance pitfalls of static model server configurations. The paper also provides practical insights for model developers and system designers, highlighting the benefits of custom kernels tailored to consumer-grade GPU architectures and the value of implementing SLO-aware scheduling strategies.

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer.

Recent works show that LLMs can generate kernels with strong performance on server GPUs. Edge deployment presents distinct challenges because the hardware is heterogeneous, the software stacks are fragmented, and the resource budgets are tight. LLM kernel generation across diverse edge backends has yet to be studied systematically. We introduce EdgeKernelBench, which combines a unified IR deployment framework with a hierarchical benchmark for edge workloads. The unified IR captures reusable computation, scheduling, and memory decisions and connects to each target backend through a compiler interface. The benchmark spans progressively larger program scopes, from individual operators to compact model graphs, across representative edge application domains. We instantiate the design with TVM as a reference compiler and validate it across heterogeneous edge backends. With a single generation attempt, the best model achieves 64.5% Correct@1 but only 25.5% Fast@1.0. This gap shows that functional correctness does not consistently translate into performance gains. We therefore introduce the Layered Edge Kernel Agent (LEKA), which organizes optimization through a layered IR. On the agent evaluation subset, LEKA achieves 43.5% Fast@1.0, compared with 13.0% for direct generation and 26.1% for Claude Code. LEKA and Claude Code use the same base model and optimization budget. Together, EdgeKernelBench and LEKA support unified evaluation and layered optimization of kernels generated by LLMs across edge backends.

GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black box and receive only errors, correctness outcomes, and timing, while existing DSLs either hide critical scheduling decisions or expose them through difficult layout abstractions. We present CAKE, a compiler-agent co-design in which agents author CAKE IR, a typed, hardware-explicit schedule representation. CAKE exposes warp roles, memory movement, synchronization, and pipelines while supporting verification, cost modeling, and localized diagnostics. The harness itself evolves: recurring failures become verifier rules, IR primitives, model calibrations, and reusable optimization tactics. In matched implementation-hidden Flash-KMeans clean starts on B200, the best CAKE IR candidate at an 80-million-token budget runs at 1.144x the tuned FlashML baseline, compared with 0.928x for direct CUDA/PTX. Beyond this benchmark, agent-generated Kimi Delta Attention achieves a 2.05x geometric-mean speedup over official FlashKDA and passes end-to-end serving validation. Dispatcher-backed KNN and KMeans improve performance by 1.42x to 2.12x across more than 400 shapes, and four kernel changes are available as upstream PRs. CAKE targets NVIDIA GPUs from Ampere through Blackwell and separates single-shape evolution from library generalization and dispatch.

Large Language Models (LLMs) have achieved strong performance across natural language and multimodal tasks, yet their practical deployment remains constrained by inference latency and kernel launch overhead, particularly in interactive, short-sequence settings. This paper presents a hybrid runtime framework that combines Just-In-Time (JIT) compilation with CUDA Graph execution to reduce launch overhead while preserving runtime flexibility during autoregressive decoding. The framework partitions transformer inference into static components executed via CUDA Graph replay and dynamic components handled through JIT-compiled kernels, enabling asynchronous graph capture and reuse across decoding steps. We evaluate the proposed approach on LLaMA-2 7B using single-GPU, batch-size-one inference across prompt lengths from 10 to 500 tokens. Experimental results show that the hybrid runtime reduces Time-to-First-Token (TTFT) by up to 66.0% and achieves lower P99 latency compared with TensorRT-LLM in this regime. These results indicate that hybrid JIT-CUDA Graph execution can effectively reduce inference latency and variance for short-sequence LLM workloads, making it a practical optimization strategy for latency-sensitive AI applications.

We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at runtime, and speedup over frontier libraries across GEMM and attention workloads on H100 and B200 GPUs. Our evaluation shows that architecture-specific PTX capability remains uneven: success rates fall substantially on complex attention backward workloads, and executing the target instructions does not necessarily translate into competitive performance. No evaluated model consistently matches frontier libraries across the suite. We further adapt Qwen3.6-27B using supervised fine-tuning. Repair-conditioned training improves several tasks, but generalization remains uneven; data coverage, balance, and the quality of the reasoning teacher matter in addition to dataset size. PTXBench provides an auditable testbed for measuring and improving LLMs' ability to exploit evolving GPU architectures.

While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient LLM inference deployments that leverage energy trade-offs of heterogeneous hardware due to a lack of energy-aware benchmarks and data. In this work we address this gap with Watt Counts: the largest open-access dataset of energy consumption of LLMs, with over 5,000 experiments for 50 LLMs across 10 NVIDIA Graphics Processing Units (GPUs) in batch and server scenarios along with a reproducible, open-source benchmark that enables community submissions to expand this dataset. Leveraging this dataset, we conduct a system-level study of LLM inference across heterogeneous GPU architectures and show that GPU selection is crucial for energy efficiency outcomes and that optimal hardware choices vary significantly across models and deployment scenarios, demonstrating the critical importance of hardware-aware deployment in heterogeneous LLM systems. Guided by our data and insights, we show that practitioners can reduce energy consumption by up to 70% in server scenarios with negligible impact on user experience, and by up to 20% in batch scenarios.

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their extreme hardware/software diversity, volatile availability, and variable network conditions render traditional schedulers ineffective, leading to suboptimal task completion. In this work, we present REACH (Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks), a Transformer-based reinforcement learning framework that redefines task scheduling as a sequence scoring problem to balance performance, reliability, cost, and network efficiency. By modeling both global GPU states and task requirements, REACH learns to adaptively co-locate computation with data, prioritize critical jobs, and mitigate the impact of unreliable resources. Extensive simulation results show that REACH improves task completion rates by up to 17%, more than doubles the success rate for high-priority tasks, and reduces bandwidth penalties by over 80% compared to state-of-the-art baselines. Stress tests further demonstrate its robustness to GPU churn and network congestion, while scalability experiments confirm its effectiveness in large-scale, high-contention scenarios.

Optimizing GPU kernels presents a significantly greater challenge for large language models (LLMs) than standard code generation tasks, as it requires understanding hardware architecture, parallel optimization strategies, and performance profiling outputs. Most existing LLM-based approaches to kernel generation rely on simple prompting and feedback loops, incorporating hardware awareness only indirectly through profiling feedback. We introduce KernelFoundry, an evolutionary framework that efficiently explores the GPU kernel design space through three key mechanisms: (1) MAP-Elites quality-diversity search with kernel-specific behavioral dimensions to sustain exploration across diverse optimization strategies; (2) meta-prompt evolution, which co-evolves prompts with kernels to uncover task-specific optimization strategies, and (3) template-based parameter optimization to tune kernels to inputs and hardware. We evaluate this framework on KernelBench, robust-kbench, and custom tasks, generating SYCL kernels as a cross-platform GPU programming model and CUDA kernels for comparison to prior work. Our approach consistently outperforms the baseline methods, achieving an average speedup of 2.3x on KernelBench for SYCL. Moreover, KernelFoundry is implemented as a distributed framework with remote access to diverse hardware, enabling rapid benchmarking and featuring a flexible user input layer that supports kernel generation for a wide range of real-world use cases beyond benchmarking.

LLM serving relies on prefix caching to improve inference performance. As growing contexts push key-value (KV) cache footprint far beyond GPU HBM and CPU DRAM capacity, KV cache is increasingly offloaded to NVMe SSDs. Unfortunately, restoring KV cache from SSDs suffers from poor I/O performance and incurs significant GPU stalls. This is primarily because the fragmented GPU memory layout results in a massive number of tiny random I/Os, rendering the low-parallelism CPU a severe bottleneck even with GPU Direct Storage (GDS), which still relies on CPU intervention to initiate each I/O and thus remains CPU-centric. This paper presents Tutti, an efficient SSD-backed KV caching solution that eliminates CPU intervention from the critical data and I/O control paths between HBM and SSDs. At the core of Tutti is a GPU-centric KV cache object store, in which the CPU is only responsible for asynchronously loading I/O kernels once per layer to the GPU. Tutti saturates NVMe SSD bandwidth and reduces GPU stalls to near zero through the following designs: (i) we provide a GPU-native object abstraction that enables bulk KV cache transfers and management; (ii) we re-architect the GPU storage stack by introducing GPU io_uring to support asynchronous GPU direct object I/O; and (iii) we propose slack-aware I/O scheduling to avoid GPU resource contention. We have implemented Tutti and integrated it to vLLM. Extensive evaluation shows that compared to the state-of-the-art GDS-enabled, SSD-backed LMCache, Tutti reduces TTFT by 78.3% under strict SLO constraints and improves the achievable request rate by 2x. The serving cost is reduced by 27%. Tutti achieves nearly the same inference performance as DRAM-backed LMCache, while providing almost infinite capacity.

We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a single GPU. Unlike traditional GPU-centric systems, MegaTrain stores parameters and optimizer states in host memory (CPU memory) and treats GPUs as transient compute engines. For each layer, we stream parameters in and compute gradients out, minimizing persistent device state. To battle the CPU-GPU bandwidth bottleneck, we adopt two key optimizations. 1) We introduce a pipelined double-buffered execution engine that overlaps parameter prefetching, computation, and gradient offloading across multiple CUDA streams, enabling continuous GPU execution. 2) We replace persistent autograd graphs with stateless layer templates, binding weights dynamically as they stream in, eliminating persistent graph metadata while providing flexibility in scheduling. On a single H200 GPU with 1.5TB host memory, MegaTrain reliably trains models up to 120B parameters. It also achieves 1.84times the training throughput of DeepSpeed ZeRO-3 with CPU offloading when training 14B models. MegaTrain also enables 7B model training with 512k token context on a single GH200.

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.

The rapid growth of large language models (LLMs) has outpaced the evolution of single-GPU hardware, making model scale increasingly constrained by memory capacity rather than computation. While modern training systems extend GPU memory through distributed parallelism and offloading across CPU and storage tiers, they fundamentally retain a GPU-centric execution paradigm in which GPUs host persistent model replicas and full autograd graphs. As a result, scaling large models remains tightly coupled to multi-GPU clusters, complex distributed runtimes, and unpredictable host memory consumption, creating substantial barriers for node-scale post-training workloads such as instruction tuning, alignment, and domain adaptation. We present Horizon-LM, a memory-centric training system that redefines the roles of CPU and GPU for large-model optimization. Horizon-LM treats host memory as the authoritative parameter store and uses GPUs solely as transient compute engines through a CPU-master, GPU-template execution model. By eliminating persistent GPU-resident modules and autograd graphs, employing explicit recomputation with manual gradient propagation, and introducing a pipelined double-buffered execution engine, Horizon-LM decouples model scale from GPU count and bounds memory usage to the theoretical parameter footprint. On a single H200 GPU with 1.5\,TB host RAM, Horizon-LM reliably trains models up to 120B parameters. On a standard single A100 machine, Horizon-LM achieves up to 12.2times higher training throughput than DeepSpeed ZeRO-3 with CPU offloading while preserving numerical correctness. Across platforms and scales, Horizon-LM sustains high device utilization and predictable memory growth, demonstrating that host memory, not GPU memory, defines the true feasibility boundary for node-scale large-model training.

While the rapid expansion of data centers poses challenges for power grids, it also offers new opportunities as potentially flexible loads. Existing power system research often abstracts data centers as aggregate resources, while computer system research primarily focuses on optimizing GPU energy efficiency and largely ignores the grid impacts of optimized GPU power consumption. To bridge this gap, we develop a GPU-to-Grid framework that couples device-level GPU control with power system objectives. We study distribution-level voltage regulation enabled by flexibility in LLM inference, using batch size as a control knob that trades off the voltage impacts of GPU power consumption against inference latency and token throughput. We first formulate this problem as an optimization problem and then realize it as an online feedback optimization controller that leverages measurements from both the power grid and GPU systems. Our key insight is that reducing GPU power consumption alleviates violations of lower voltage limits, while increasing GPU power mitigates violations near upper voltage limits in distribution systems; this runs counter to the common belief that minimizing GPU power consumption is always beneficial to power grids.

Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capacity with CPU memory. Existing offloading systems, however, typically rely on coarse layer-level or expert-level scheduling, which overlooks substantial heterogeneity among tensors within the same layer and adapts poorly to changing hardware load conditions on such devices. This paper presents ATSInfer, a hybrid CPU-GPU inference system for consumer devices that performs offloading at tensor granularity. ATSInfer combines static tensor placement with load-aware dynamic transfer, and introduces asynchronous CPU-GPU coordination to efficiently schedule hardware storage, data movement, and computation across heterogeneous backends. We implement ATSInfer and evaluate it on representative consumer platforms using both dense and MoE models. Compared with existing systems, ATSInfer improves prefill throughput by up to 1.94times and decode throughput by up to 3.29times, while also increasing GPU utilization and making more effective use of PCIe bandwidth. These results show that ATSInfer can substantially improve the user experience of local LLM deployment on personal consumer devices.

Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while producing realistic motion. Recent Deep RL approaches, particularly imitation learning methods such as DeepMimic, have had broad impact beyond animation, influencing robotics by enabling agile and expressive behaviors. While these approaches achieve impressive results, they remain computationally inefficient to train in practice. Despite GPU-accelerated simulation, we find that end-to-end pipelines often underutilize hardware due to overheads outside the physics solver, caused by fragmented GPU kernels and CPU memory access in the critical path. We present InstantMimic, a system that addresses these inefficiencies by making the entire training loop GPU-native. Built on a GPU-native physics backend, our unified pipeline integrates simulation, environment computation, policy inference, and policy updates within a single execution flow. As a result, InstantMimic reduces training time for diverse physics-based skills to a few seconds and makes LLM-agent-driven hyperparameter search practical.

Analytical framework for predicting General Matrix Multiplication (GEMM) performance on modern GPUs, focusing on runtime, power consumption, and energy efficiency. Our study employs two approaches: a custom-implemented tiled matrix multiplication kernel for fundamental analysis, and NVIDIA's CUTLASS library for comprehensive performance data collection across advanced configurations. Using the NVIDIA RTX 4070 as our experimental platform, we developed a Random Forest-based prediction model with multi-output regression capability. Through analysis of both naive tiled matrix multiplication with varying tile sizes (1 to 32) and 16,128 CUTLASS GEMM operations across diverse configurations, we identified critical performance patterns related to matrix dimensions, thread block configurations, and memory access patterns. Our framework achieved exceptional accuracy with an R^2 score of 0.98 for runtime prediction (mean error 15.57%) and 0.78 for power prediction (median error 5.42%). The system successfully predicts performance across matrix sizes, demonstrating robust scaling behavior. Our results show that optimal tile size selection can improve performance by up to 3.2x while reducing power consumption by 22% compared to baseline configurations. Analysis of shared memory utilization and SM occupancy reveals that tile sizes of 16x16 achieve the best balance between parallelism and resource usage. The implementation of our framework, including prediction models and analysis tools, is available as an open-source project at GPPerf [https://github.com/pavlyhalim/GPPerf].

Fine-tuning large pre-trained LLMs generally demands extensive GPU memory. Traditional first-order optimizers like SGD encounter substantial difficulties due to increased memory requirements from storing activations and gradients during both the forward and backward phases as the model size expands. Alternatively, zeroth-order (ZO) techniques can compute gradients using just forward operations, eliminating the need to store activations. Furthermore, by leveraging CPU capabilities, it's feasible to enhance both the memory and processing power available to a single GPU. We propose a novel framework, ZO2 (Zeroth-Order Offloading), for efficient zeroth-order fine-tuning of LLMs with only limited GPU memory. Our framework dynamically shifts model parameters between the CPU and GPU as required, optimizing computation flow and maximizing GPU usage by minimizing downtime. This integration of parameter adjustments with ZO's double forward operations reduces unnecessary data movement, enhancing the fine-tuning efficacy. Additionally, our framework supports an innovative low-bit precision approach in AMP mode to streamline data exchanges between the CPU and GPU. Employing this approach allows us to fine-tune extraordinarily large models, such as the OPT-175B with more than 175 billion parameters, on a mere 18GB GPU--achievements beyond the reach of traditional methods. Moreover, our framework achieves these results with almost no additional time overhead and absolutely no accuracy loss compared to standard zeroth-order methods. ZO2's code has been open-sourced in https://github.com/liangyuwang/zo2.

NVIDIA Grace--Blackwell systems make CPU--GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA managed allocation on GB200 may be served from GPU-local HBM, accessed through host/system memory, demand-migrated, prefetched, reused after GPU access, or evicted and reloaded under capacity pressure. The problem is that these states share a programming interface while exercising different hardware paths and runtime mechanisms, making a single ``Unified Memory bandwidth'' number misleading. This paper presents a placement-controlled microbenchmark study of CUDA Unified Memory on NVIDIA GB200, using GH200 as a Grace--Hopper baseline and GB10/DGX Spark as a validation platform. Our methodology separates local HBM access, host/system-memory access, explicit movement, managed first touch, prefetch, reuse, access-pattern sensitivity, oversubscription, and CPU--GPU handoff, then summarizes the observations with a measurement-calibrated model of compute, access, migration, eviction, synchronization, and handoff costs. On GB200, a 1~GB STREAM-style triad reaches 3963~GB/s from local HBM but 304~GB/s through host-mapped CPU/system memory; for a 256~MB streaming kernel, cold CPU-initialized managed memory reaches 14.1~GB/s, while managed prefetch and reuse reach 4606~GB/s and 4504~GB/s. Below the capacity boundary, prefetched and reused managed memory remain above 4.6~TB/s, but at 125\% of CUDA-visible memory they fall to 968~GB/s and 1214~GB/s, showing that Grace--Blackwell unified memory must be understood through placement, access history, locality, reuse, and capacity pressure.

MPI derived datatypes are an abstraction that simplifies handling of non-contiguous data in MPI applications. These datatypes are recursively constructed at runtime from primitive Named Types defined in the MPI standard. More recently, the development and deployment of CUDA-aware MPI implementations has encouraged the transition of distributed high-performance MPI codes to use GPUs. Such implementations allow MPI functions to directly operate on GPU buffers, easing integration of GPU compute into MPI codes. This work first presents a novel datatype handling strategy for nested strided datatypes, which finds a middle ground between the specialized or generic handling in prior work. This work also shows that the performance characteristics of non-contiguous data handling can be modeled with empirical system measurements, and used to transparently improve MPI_Send/Recv latency. Finally, despite substantial attention to non-contiguous GPU data and CUDA-aware MPI implementations, good performance cannot be taken for granted. This work demonstrates its contributions through an MPI interposer library, TEMPI. TEMPI can be used with existing MPI deployments without system or application changes. Ultimately, the interposed-library model of this work demonstrates MPI_Pack speedup of up to 242000x and MPI_Send speedup of up to 59000x compared to the MPI implementation deployed on a leadership-class supercomputer. This yields speedup of more than 917x in a 3D halo exchange with 3072 processes.

The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, thread scheduling, and hardware-specific characteristics. While recent advances in large language models (LLMs) provide new opportunities for automated code generation, existing approaches largely treat LLMs as single-shot generators or naive refinement tools, limiting their effectiveness in navigating the irregular kernel optimization landscape. We introduce an LLM agentic framework for GPU kernel optimization that systematically explores the design space through multi-agent collaboration, grounded instruction, dynamic context management, and strategic search. This framework mimics the workflow of expert engineers, enabling LLMs to reason about hardware trade-offs, incorporate profiling feedback, and refine kernels iteratively. We evaluate our approach on KernelBench, a benchmark for LLM-based kernel optimization, and demonstrate substantial improvements over baseline agents: our system produces correct solutions where baselines often fail, and achieves kernels with up to 16x faster runtime performance. These results highlight the potential of agentic LLM frameworks to advance fully automated, scalable GPU kernel optimization.

Mixture-of-experts models make nearly trillion-parameter capacity accessible with sparse per-token computation, provided that the serving system can distribute the weights and coordinate their execution. We present Cascadia's resident execution of Inkling, a 975B-total/41B-active-parameter model, on eleven Intel Core Ultra X7 358H AI PCs, each with 64 GB of memory, Arc B390 integrated graphics and gigabit Ethernet. We contribute a custom resident MoE engine that preserves Inkling's routing rules, constructs compressed graphs for OpenVINO's fused iGPU primitives, and coordinates FP16 expert computation with FP32 output restoration. The engine fits six consecutive decoder layers per machine and represents dense feed-forward blocks as all-active expert slices, reducing measured dense-layer call time from approximately 8.1 to 4.5 ms. A streaming pipeline coordinates concurrent generation, while captured-state draft evaluation measures agreement with the deployed numerical path. Paired measurements at fifteen concurrency levels from 1 to 176 streams reach 60.29 aggregate decode tokens/s at 88 streams, with 46.87 tokens/s over the complete serving phases. At fifteen streams, median first-token latency is 6.05 s. Raising the context budget from the 1,024-position default, real prompts of 1k to 64k tokens recover the embedded code in all 19 measured answers, with first-token time growing as aN+bN^2 and decode latency growing approximately linearly, both bounded by a single-threaded CPU attention loop rather than by memory, which holds 512k positions per stream. Evaluation on captured fleet states separates the effects of vocabulary selection and weight quantization on draft agreement. Together, these contributions establish an execution and evaluation approach for large sparse models on distributed client systems with shared CPU-GPU memory.

The rapid growth of large-language models (LLMs) is driving a new wave of specialized hardware for inference. This paper presents the first workload-centric, cross-architectural performance study of commercial AI accelerators, spanning GPU-based chips, hybrid packages, and wafer-scale engines. We compare memory hierarchies, compute fabrics, and on-chip interconnects, and observe up to 3.7x performance variation across architectures as batch size and sequence length change. Four scaling techniques for trillion-parameter models are examined; expert parallelism offers an 8.4x parameter-to-compute advantage but incurs 2.1x higher latency variance than tensor parallelism. These findings provide quantitative guidance for matching workloads to accelerators and reveal architectural gaps that next-generation designs must address.

This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various LLMs and token lengths, with a particular focus on the bottleneck caused by CPU-GPU data transfers via PCIe. Our results indicate that while there is minimal computational overhead within the GPU, the overall performance penalty is primarily attributable to data transfer. For the majority of typical LLM queries, the overhead remains below 7%, with larger models and longer sequences experiencing nearly zero overhead.

Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a handful of AIPCs, working together over an ordinary network, can serve models beyond the capability of any single one. We use pipeline parallelism: a model is split by layer into per-stage shards, each pre-compiled into an OpenVINO graph, so that every machine runs one shard and passes activations to the next. Three techniques make this fast enough to be useful. First, we recover the speed of the unsplit model: a naive per-stage export runs well below monolithic inference because it misses an OpenVINO GPU optimization, and injecting a beam_idx Gather into each shard triggers that optimization (the IndirectKVCache fusion) and brings the shards to parity. Second, we leverage speculative decoding on stateful OpenVINO models. Third, the pipeline serves several users at once by interleaving their requests across the stages, each request carrying its own cache (micro-batching). Together, a two-node Llama 3.1 8B INT4 pipeline serves two concurrent users at 1.79x the single-user throughput of the unsplit model on the same hardware, and the gap widens under simulated wide-area latency. The same design scales to a 70B model that no single fleet member can hold: a four-node deployment of Lunar Lake AI PCs on Intel Tiber Cloud serves a single user at interactive speed, with output token-for-token identical to the same four-node pipeline decoding without speculation. Code, raw benchmark logs, and reproduction scripts ship as a self-contained package at https://github.com/labscommunity/pipeline-sharded-inference-paper (in the top-level reproduction/ directory).

AI systems can now write and optimize production GPU kernels, but validating them remains an important challenge. Evaluating the kernel on a few random inputs and checking that its outputs match a trusted reference kernel within numeric tolerances is not sufficient: races can cause nondeterministic behavior that fails to manifest in tests, and numeric tolerances can hide bugs and cause false positives even after extensive calibration. To address this challenge, we present RESOLVE, which combines testing and formal verification to build a comprehensive kernel validation pipeline. It operates in three steps: First, it tests for nondeterminism using binary instrumentation that perturbs execution timing to expose races. Second, an agent rewrites the candidate and reference kernels to obtain "reduced-concurrency" versions that are simpler to analyze but still produce bitwise-identical outputs in all tests. Third, the reduced kernels are formally analyzed in the F*/Pulse framework and prove that they perform the same computation on real numbers. This sidesteps the need for numeric tolerances. We show that RESOLVE can validate a broad selection of kernels using KernelBench, and prove equivalence across fused GEMMs in three state-of-the-art frameworks and languages: CUTLASS, Triton, and Gluon. It also analyzes mega-kernels, notoriously difficult to validate, and finds four previously unreported issues, including two clear bugs. We show that agents can use RESOLVE to repair the issues, with minimal performance impact, highlighting that agents can optimize aggressively when they can rigorously check their results.

To match the blooming demand of generative AI workloads, GPU designers have so far been trying to pack more and more compute and memory into single complex and expensive packages. However, there is growing uncertainty about the scalability of individual GPUs and thus AI clusters, as state-of-the-art GPUs are already displaying packaging, yield, and cooling limitations. We propose to rethink the design and scaling of AI clusters through efficiently-connected large clusters of Lite-GPUs, GPUs with single, small dies and a fraction of the capabilities of larger GPUs. We think recent advances in co-packaged optics can be key in overcoming the communication challenges of distributing AI workloads onto more Lite-GPUs. In this paper, we present the key benefits of Lite-GPUs on manufacturing cost, blast radius, yield, and power efficiency; and discuss systems opportunities and challenges around resource, workload, memory, and network management.

With the rise of AI, NVIDIA GPUs have become the de facto standard for AI system design. This paper presents a comprehensive evaluation of Intel Gaudi NPUs as an alternative to NVIDIA GPUs for AI model serving. First, we create a suite of microbenchmarks to compare Intel Gaudi-2 with NVIDIA A100, showing that Gaudi-2 achieves competitive performance not only in primitive AI compute, memory, and communication operations but also in executing several important AI workloads end-to-end. We then assess Gaudi NPU's programmability by discussing several software-level optimization strategies to employ for implementing critical FBGEMM operators and vLLM, evaluating their efficiency against GPU-optimized counterparts. Results indicate that Gaudi-2 achieves energy efficiency comparable to A100, though there are notable areas for improvement in terms of software maturity. Overall, we conclude that, with effective integration into high-level AI frameworks, Gaudi NPUs could challenge NVIDIA GPU's dominance in the AI server market, though further improvements are necessary to fully compete with NVIDIA's robust software ecosystem.

Training transformer models requires substantial GPU compute and memory resources. In homogeneous clusters, distributed strategies allocate resources evenly, but this approach is inefficient for heterogeneous clusters, where GPUs differ in power and memory. As high-end GPUs are costly and limited in availability, heterogeneous clusters with diverse GPU types are becoming more common. Existing methods attempt to balance compute across GPUs based on capacity but often underutilize compute due to memory constraints. We present Cephalo, a system that optimizes compute and memory usage by decoupling compute distribution from training state assignment. Cephalo outperforms state-of-the-art methods by achieving significantly higher training throughput while supporting larger models and batch sizes.

W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed-precision fallbacks. We present the first systematic study of how intra-SM compute balance governs this bottleneck. Through controlled benchmarks across four GPUs from Ampere and Ada architectures, we identify the Tensor Cores to CUDA Cores throughput ratio (ρ) as the primary hardware indicator: the W4A4-g128 kernel yields 2.0--2.5times speedup on RTX~3090 (ρ=16) yet degrades to 0.43--0.47times on A100 (ρ=64) in compute-bond scenarios, establishing W4A4 viability as platform-dependent rather than universally infeasible. Guided by this finding, we build APEX4, which co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to mitigate the CUDA Cores dequantization bottleneck. APEX4 achieves perplexity within 0.63 of FP16 on LLaMA-2-70B and outperforms W4Ax Atom-g128 by 4.0\%--4.4\% in zero-shot accuracy. Deployed as a drop-in replacement in unmodified vLLM, it delivers up to 1.66times end-to-end speedup on L40S (ρ=8), and 1.78times on RTX~3090 (ρ=16), 2.09times on A40 (ρ=16), while recovering A100 (ρ=64) to 1.20--1.40times via the mixed-granularity mode. Our code is available at https://github.com/APEX4-W4A4/APEX4-W4A4.

AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic workloads are dynamic and structurally complex. Often these agents are directed graphs of compute and IO operations that span multi-modal data input and conversion), data processing and context gathering (e.g vector DB lookups), multiple LLM inferences, tool calls, etc. To scale AI agent usage, we need efficient and scalable deployment and agent-serving infrastructure. To tackle this challenge, in this paper, we present a system design for dynamic orchestration of AI agent workloads on heterogeneous compute infrastructure spanning CPUs and accelerators, both from different vendors and across different performance tiers within a single vendor. The system delivers several building blocks: a framework for planning and optimizing agentic AI execution graphs using cost models that account for compute, memory, and bandwidth constraints of different HW; a MLIR based representation and compilation system that can decompose AI agent execution graphs into granular operators and generate code for different HW options; and a dynamic orchestration system that can place the granular components across a heterogeneous compute infrastructure and stitch them together while meeting an end-to-end SLA. Our design performs a systems level TCO optimization and preliminary results show that leveraging a heterogeneous infrastructure can deliver significant TCO benefits. A preliminary surprising finding is that for some workloads a heterogeneous combination of older generation GPUs with newer accelerators can deliver similar TCO as the latest generation homogenous GPU infrastructure design, potentially extending the life of deployed infrastructure.

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism suffer from noticeable generation artifacts and fail to achieve substantial acceleration proportional to the number of GPUs. Therefore, we propose a hybrid parallelism framework that combines a novel data parallel strategy, condition-based partitioning, with an optimal pipeline scheduling method, adaptive parallelism switching, to reduce generation latency and achieve high generation quality in conditional diffusion models. The key ideas are to (i) leverage the conditional and unconditional denoising paths as a new data-partitioning perspective and (ii) adaptively enable optimal pipeline parallelism according to the denoising discrepancy between these two paths. Our framework achieves 2.31times and 2.07times latency reductions on SDXL and SD3, respectively, using two NVIDIA RTX~3090 GPUs, while preserving image quality. This result confirms the generality of our approach across U-Net-based diffusion models and DiT-based flow-matching architectures. Our approach also outperforms existing methods in acceleration under high-resolution synthesis settings. Code is available at https://github.com/kaist-dmlab/Hybridiff.

High-performance GPU kernel optimization remains a critical yet labor-intensive task in modern machine learning workloads. Although Triton, a domain-specific language for GPU programming, enables developers to write efficient kernels with concise code, achieving expert-level performance still requires deep understanding of GPU architectures and low-level performance trade-offs. We present TritonForge, a profiling-guided framework for automated Triton kernel optimization. TritonForge integrates kernel analysis, runtime profiling, and iterative code transformation to streamline the optimization process. By incorporating feedback from profiling results, the system identifies performance bottlenecks, proposes targeted code modifications, and evaluates their impact automatically. Across diverse kernel types, TritonForge achieves up to 5x performance improvement over baseline implementations and on average 1.76x of the cases are successful, providing a foundation for future research in automated GPU performance optimization.

Modern cutting-edge AI applications are being developed over fast-evolving, heterogeneous, nascent hardware devices. This requires frequent reworking of the AI software stack to adopt bottom-up changes from new hardware, which takes time for general-purpose software libraries. Consequently, real applications often develop custom software stacks optimized for their specific workloads and hardware. Custom stacks help in quick development and optimization, but incur a lot of redundant efforts across applications in writing non-portable code. This paper discusses an alternative communication library interface for AI applications that offers both portability and performance by reducing redundant efforts while maintaining flexibility for customization. We present MSCCL++, a novel abstraction of GPU communication based on separation of concerns: (1) a primitive interface provides a minimal hardware abstraction as a common ground for software and hardware developers to write custom communication, and (2) higher-level portable interfaces and specialized implementations enable optimization for different workloads and hardware environments. This approach makes the primitive interface reusable across applications while enabling highly flexible optimization. Compared to state-of-the-art baselines (NCCL, RCCL, and MSCCL), MSCCL++ achieves speedups of up to 5.4times for collective communication and up to 15% for real-world AI inference workloads. MSCCL++ is in production of multiple AI services provided by Microsoft Azure, and is also adopted by RCCL, the GPU collective communication library maintained by AMD. MSCCL++ is open-source and available at https://github.com/microsoft/mscclpp.

Recent CUDA exploitation work shows that GPU memory bugs can escalate into device-side control-flow corruption, as kernels later consume corrupted return continuations, function pointers, dispatch-table entries, or branch targets. For deployed CUDA binaries, the relevant security boundary is executed NVIDIA SASS, after PTX lowering, inlining, ABI decisions, register allocation, spills, predication, and SIMT execution; source- or PTX-level policies do not capture this boundary. We present WarpGuard, to our knowledge the first protected-site CFI system for CUDA device binaries operating on executed SASS. WarpGuard enforces at protected sites: recovered SASS instructions or sequences that consume control-flow state, provide sufficient binary evidence to derive policy, are checked before release, and fail closed on violation. It authenticates backward-edge continuation state for instrumented returns, validates recoverable forward targets per site, and reports fixed-edge, unsupported, profile-excluded, fallback, and no-surface outcomes outside the protected denominator. On 77 CUDA artifacts, WarpGuard classifies 51,621 SASS control-flow sites, including 1,343 returns and 154 supported forward target-set entries, and records 52.2 million dynamic checks. In representative backward- and forward-edge corruption attacks, native execution reaches attacker-selected behavior, detect-only mode records the expected violation, and enforcement fails closed before releasing the invalid protected transfer. Public-code evidence shows that the same SASS consumption patterns occur in real CUDA systems, including runtime dispatch tables, cuFFT callbacks, generated callable tables, and uploaded device-function pointers. WarpGuard delivers auditable protected-site CFI for CUDA SASS and separates dynamic-instrumentation enforcement from callback-free SASS timing and patch-cache feasibility.

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.

JET uses pretrained language and vision-language models to select among a finite set of answers without additional training. It evaluates candidate likelihoods directly and shares computation across candidates. Experiments on desktop CPUs and consumer GPUs assess decision accuracy and execution cost. Qwen3.6-35B-A3B achieves 87.48% accuracy on the full MMLU test set and 3.69 requests per second on a separately timed MMLU subset. The accuracy-throughput comparison covers model, hardware, and reasoning choices, with Jev as an external reference. Controlled execution experiments show 2.18-2.23-fold speedups from prefix reuse and cache management, and a 30.8% reduction in process time from input preparation optimizations, with unchanged outputs. Optional reasoning has a task-dependent accuracy-throughput trade-off. These results support local decision inference from existing models.

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.

Monolithic serving with chunked prefill improves GPU utilization by batching prefill and decode together, but suffers from fine-grained phase interference. Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead. Prior intra-GPU disaggregation approaches multiplex prefill and decode within a single GPU, using SLO-based tuning guided by heuristics from offline profiling or reactive feedback loops. However, these methods respond reactively to performance issues rather than anticipating them, limiting adaptability under dynamic workloads. We ask: can we achieve proactive intra-GPU disaggregation that adapts effectively to dynamic workloads? The key challenge lies in managing the conflicting resource demands of prefill and decode under varying conditions. We first show that GPU resources exhibit diminishing returns -- beyond a saturation point, more allocation yields minimal latency benefit. Second, we observe that memory bandwidth contention becomes a critical bottleneck. These insights motivate a design that dynamically partitions GPU resources across prefill and decode phases, while jointly considering compute capacity, memory footprint, and bandwidth contention. Evaluated on diverse LLMs and workloads, our system Nexus achieves up to 2.2x higher throughput, 20x lower TTFT, and 2.5x lower TBT than vLLM; outperforms SGLang by up to 2x; and matches or exceeds disaggregated vLLM.

Large language models (LLMs) require vast amounts of GPU compute to train, but limited availability and high costs of GPUs make homogeneous clusters impractical for many organizations. Instead, assembling heterogeneous clusters by pooling together GPUs of different generations allows them to achieve higher aggregate compute and make use of all available GPUs. However, training on heterogeneous clusters presents several challenges, including load balancing across GPUs, optimizing memory usage to accommodate varying memory capacities, and ensuring communication-efficient training over diverse network interconnects potentially spanning multiple datacenters. In this paper, we make the case that efficient training on heterogeneous clusters requires (1) the integration of pipeline parallelism and data parallelism in a manner that is both communication- and memory-efficient, and (2) a more adaptable configuration of pipeline and data parallelism, which includes the capability to flexibly partition GPUs into asymmetric pipeline parallel stages and to incorporate heterogeneous GPUs within the same data parallelism group. We propose Zorse, the first system to unify all these capabilities while incorporating a planner that automatically configures training strategies for a given workload. Our evaluation shows that Zorse significantly outperforms state-of-the-art systems in heterogeneous training scenarios.

Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness in service evaluation, wasting limited resources, and (2) use heuristic strategies to decide admission and placement on GPUs, resulting in suboptimal scheduling decisions. To bridge this gap, we present TAO, a tool-aware joint scheduling framework for LLM-based agentic serving. Its value interface combines near-term tool readiness, node-specific cache credit with time-aware decay, and token footprint; a dynamic program jointly selects and places waiting sessions under capacity constraints. Across the 12 reported model-workload-concurrency settings, TAO reduces latency by up to 26.8%, reduces mean time to first token (TTFT) by up to 36.3%, and increases decode throughput by up to 29.5% relative to the best evaluated state-of-the-art baseline for each metric.

Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. Nonetheless, this encryption incurs a significant performance overhead, reaching up to 52.8 percent and 88.2 percent throughput drop when serving OPT-30B and OPT-66B, respectively. To address this challenge, we introduce PipeLLM, a user-transparent runtime system. PipeLLM removes the overhead by overlapping the encryption and GPU computation through pipelining - an idea inspired by the CPU instruction pipelining - thereby effectively concealing the latency increase caused by encryption. The primary technical challenge is that, unlike CPUs, the encryption module lacks prior knowledge of the specific data needing encryption until it is requested by the GPUs. To this end, we propose speculative pipelined encryption to predict the data requiring encryption by analyzing the serving patterns of LLMs. Further, we have developed an efficient, low-cost pipeline relinquishing approach for instances of incorrect predictions. Our experiments on NVIDIA H100 GPU show that compared with vanilla systems without confidential computing (e.g., vLLM, PEFT, and FlexGen), PipeLLM incurs modest overhead (less than 19.6 percent in throughput) across various LLM sizes, from 13B to 175B.

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference, characterized by a power-law distribution in neuron activation. This distribution indicates that a small subset of neurons, termed hot neurons, are consistently activated across inputs, while the majority, cold neurons, vary based on specific inputs. PowerInfer exploits such an insight to design a GPU-CPU hybrid inference engine: hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons are computed on the CPU, thus significantly reducing GPU memory demands and CPU-GPU data transfers. PowerInfer further integrates adaptive predictors and neuron-aware sparse operators, optimizing the efficiency of neuron activation and computational sparsity. Evaluation shows that PowerInfer attains an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs (including OPT-175B) on a single NVIDIA RTX 4090 GPU, only 18% lower than that achieved by a top-tier server-grade A100 GPU. This significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy.

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that struggle to adapt to dynamic workload conditions, leading to substantial inefficiencies. We present FlexPipe, a novel system that dynamically reconfigures pipeline architectures during runtime to address these fundamental limitations. FlexPipe decomposes models into fine-grained stages and intelligently adjusts pipeline granularity based on real-time request pattern analysis, implementing three key innovations: fine-grained model partitioning with preserved computational graph constraints, inflight pipeline refactoring with consistent cache transitions, and topology-aware resource allocation that navigates GPU fragmentation. Comprehensive evaluation on an 82-GPU cluster demonstrates that FlexPipe achieves up to 8.5x better resource efficiency while maintaining 38.3% lower latency compared to state-of-the-art systems, reducing GPU reservation requirements from 75% to 30% of peak capacity.

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization and throughput at the cost of increased latency per token. In contrast, disaggregated serving decouples compute-bound prefill and bandwidth-bound decode phases to optimize for service level objectives (SLOs) at the cost of resource under-utilization and KV-cache transfer overheads. To address the limitations of these techniques, we propose RAPID-Serve: a technique to concurrently execute prefill and decode on the same GPU(s) to meet latency SLOs while maintaining high throughput and efficient resource utilization. Furthermore, we propose Adaptive Resource Management for runtime compute resource allocation, optionally leveraging CU masking (a fine-grained Compute Unit partitioning feature on AMD InstinctTM GPUs). RAPID-Serve provides up to 4.1x (average 1.7x) unconstrained throughput improvement and 32x and higher (average 4.9x) throughput improvement under SLO constraints, showing it as an effective strategy compared to the state-of-the-art approaches, particularly in resource-constrained environments.

Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for arbitrary PyTorch models. Given a model, AutoKernel profiles it to identify computational bottlenecks, ranks them by Amdahl's law impact, and iteratively refines Triton or CUDA C++ kernel implementations through hundreds of experiments without human intervention. A five-stage correctness harness covering smoke tests, shape sweeps, numerical stability, determinism verification, and edge-case coverage ensures every candidate kernel is validated before any speedup is recorded. The system comprises over 9,000 lines of Python, 18 starter kernel implementations across two backends, a six-tier optimization playbook, and integration with the KernelBench benchmark suite. AutoKernel covers nine kernel types spanning the dominant operations in modern transformer architectures. On an NVIDIA H100, our Triton kernels outperform both PyTorch eager and torch.compile (max-autotune) on the majority of tested configurations: 5.29x over eager on RMSNorm, 2.82x on softmax, and 2.21x on cross-entropy, while beating torch.compile by 2.83x, 3.44x, and 2.94x respectively. In community deployment, an AutoKernel-optimized kernel achieved first place on the vectorsum_v2 B200 leaderboard. The full system is available at https://github.com/RightNow-AI/autokernel.

Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions that generate video progressively, chunk by chunk. Unlike offline video generation or typical LLM serving, streaming video generation must preserve session state across active and idle periods, repeatedly schedule ongoing sessions, and deliver each chunk under a tight latency target. This creates two key serving challenges in multi-user, multi-GPU environments: session duration heterogeneity, where long-running sessions make placement decisions suboptimal over time, and temporal user-demand heterogeneity, where the number of active sessions fluctuates sharply across bursts and idle periods. We present TurboServe, the first serving system designed specifically for streaming video generation workloads. TurboServe formulates serving as an online scheduling problem that jointly coordinates session placement and GPU provisioning. Its closed-loop scheduling algorithm combines a migration-aware placement controller, which rebalances sessions across GPUs to reduce the maximum per-chunk latency, with a load-driven autoscaling controller, which adapts the GPU budget to workload variation for improved cost efficiency. To support these decisions at runtime, TurboServe implements coalesced chunk processing for batching concurrent active sessions on the same GPU, GPU-CPU offloading for session suspension and resumption, and NCCL-based GPU-GPU migration for online rebalancing. We evaluate TurboServe on real-world production traces from Shengshu Technology across multiple model sizes and GPU clusters with up to 64 NVIDIA B300 GPUs. Compared with baseline serving configurations, TurboServe reduces worst-case per-chunk latency by 37.5% and total GPU operating cost by 37.2% on average. Our code is publicly available at https://github.com/shengshu-ai/TurboServe.

Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM serving: single-stream, batch-1 autoregressive decode, where one robot, camera feed or user session waits on the next token. This workload is usually described as memory-bandwidth-bound. Each decode step streams model weights and the active KV cache, so latency should scale with peak HBM bandwidth. We show that this account is true but incomplete. We measure batch-1 decode for three 7 to 8B-class GQA transformers across four NVIDIA GPUs: H100 SXM5, A100-80GB SXM4, L40S and L4. We evaluate context lengths from 2048 to 16384, producing 44 valid cells under a controlled bf16 SDPA setup. The achieved fraction of peak HBM bandwidth falls as peak bandwidth rises. On the headline Qwen-2.5-7B ctx=2048 cell, an L4 reaches roughly 81 percent of its analytic memory floor, while an H100 reaches only 27 percent. Physical-AI decode is memory-dominated, but faster memory does not translate into proportional latency gains. We test the missing term with a CUDA Graphs A/B experiment. On H100 at ctx=2048, CUDA Graphs improves decode latency by 1.259x across N=10 fresh sessions, with a 95 percent bootstrap confidence interval of 1.253 to 1.267. On L4, the same intervention gives only 1.028x. This isolates a launch-side overhead that becomes visible on fast GPUs but remains mostly hidden on slower, bandwidth-bound GPUs. The deployment implication is that memory savings matter only when the runtime realises them. On L4, bf16 decode sits close to the memory floor, but common quantised paths do not recover the expected 4x weight-traffic reduction: bnb-nf4 reaches 59.36 ms/step and AutoAWQ+Marlin reaches 45.24 ms/step from a 62.32 ms bf16 baseline. GPTQ+ExLlamaV2, with Ada-tuned int4 kernels, reaches 17.36 ms/step.

Deploying advanced large language models on edge devices, such as smartphones and robotics, is a growing trend that enhances user data privacy and network connectivity resilience while preserving intelligent capabilities. However, such a task exhibits single-batch computing with incredibly low arithmetic intensity, which poses the significant challenges of huge memory footprint and bandwidth demands on limited edge resources. To address these issues, we introduce Cambricon-LLM, a chiplet-based hybrid architecture with NPU and a dedicated NAND flash chip to enable efficient on-device inference of 70B LLMs. Such a hybrid architecture utilizes both the high computing capability of NPU and the data capacity of the NAND flash chip, with the proposed hardware-tiling strategy that minimizes the data movement overhead between NPU and NAND flash chip. Specifically, the NAND flash chip, enhanced by our innovative in-flash computing and on-die ECC techniques, excels at performing precise lightweight on-die processing. Simultaneously, the NPU collaborates with the flash chip for matrix operations and handles special function computations beyond the flash's on-die processing capabilities. Overall, Cambricon-LLM enables the on-device inference of 70B LLMs at a speed of 3.44 token/s, and 7B LLMs at a speed of 36.34 token/s, which is over 22X to 45X faster than existing flash-offloading technologies, showing the potentiality of deploying powerful LLMs in edge devices.

Mixture-of-Experts (MoE) model architecture has emerged as a promising solution for scaling transformer models efficiently, offering sparse activation that reduces computational costs while increasing model capacity. However, as MoE models scale, they need to be distributed across GPU devices, thus face critical performance bottlenecks due to their large memory footprint. Expert parallelism distributes experts across GPUs, however, faces key challenges including an unbalanced token routing and expert activation, resulting in communication tail latency and processing inefficiencies. While existing solutions address some of these issues, they fail to resolve the dual challenges of load imbalance and communication skew. The imbalance in token processing load across experts causes uneven processing times on different GPUs, while communication skew between GPUs leads to unbalanced inter-GPU data transfers. These factors degrade the performance of MoE models by increasing tail latency and reducing overall throughput. To address these limitations, we propose an Integer Linear Programming (ILP) formulation to optimize expert placement by jointly considering token load, communication, and computation costs. We exploit the property that there is a token routing dependency across layers, where tokens routed to a specific expert in one layer are likely to be routed to a limited set of experts in the subsequent layer. Our solution, MoETuner, offers an optimal expert-to-GPU assignment that minimizes inter-GPU token routing costs and balances token processing across devices, thereby reducing tail latency and end-to-end execution time. Experimental results demonstrate 9.3% and 17.5% of end-to-end speedups for single-node and multi-node inference respectively, showcasing the potential of our ILP-based optimization for offering expert parallel solutions for next-generation MoEs.

Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute budgets, yet the specialized expertise required for manual optimization remains a niche and scarce skillset. This challenge is particularly evident in managing GPU utilization across heterogeneous infrastructure while enabling teams with diverse workloads and limited LLM optimization experience to deploy models efficiently. We present OptiKIT, a distributed LLM optimization framework that democratizes model compression and tuning by automating complex optimization workflows for non-expert teams. OptiKIT provides dynamic resource allocation, staged pipeline execution with automatic cleanup, and seamless enterprise integration. In production, it delivers more than 2x GPU throughput improvement while empowering application teams to achieve consistent performance improvements without deep LLM optimization expertise. We share both the platform design and key engineering insights into resource allocation algorithms, pipeline orchestration, and integration patterns that enable large-scale, production-grade democratization of model optimization. Finally, we open-source the system to enable external contributions and broader reproducibility.

Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose one-for-many GPU prewarming, which proactively loads parameters from multiple models onto GPUs based on workload forecasts. These prewarmed weights enable the system to promptly instantiate serving instances upon encountering request bursts. We design and implement WarmServe, a multi-LLM serving system incorporating three key techniques: (1) a model placement algorithm that optimizes prewarming decisions to minimize cross-model prewarming interference, (2) a KV cache reservation strategy that repurposes idle KV cache space on running GPUs for prewarming new models, and (3) an efficient GPU memory switching mechanism for tensor management. Evaluation on real-world datasets shows that WarmServe reduces tail TTFT by up to 50.8times compared to the state-of-the-art autoscaling-based system, while supporting up to 2.5times higher request throughput than the GPU-sharing system.

Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution. Existing automated approaches typically treat Large Language Models (LLMs) merely as stochastic code generators within heuristic-guided evolutionary loops. These methods often struggle with complex kernels requiring coordinated, multi-step structural transformations, as they lack explicit planning capabilities and frequently discard promising strategies due to inefficient or incorrect intermediate implementations. To address this, we propose Search via Co-Evolving World Model and build K-Search based on this method. By replacing static search heuristics with a co-evolving world model, our framework leverages LLMs' prior domain knowledge to guide the search, actively exploring the optimization space. This approach explicitly decouples high-level algorithmic planning from low-level program instantiation, enabling the system to navigate non-monotonic optimization paths while remaining resilient to temporary implementation defects. We evaluate K-Search on diverse, complex kernels from FlashInfer, including GQA, MLA, and MoE kernels. Our results show that K-Search significantly outperforms state-of-the-art evolutionary search methods, achieving an average 2.10x improvement and up to a 14.3x gain on complex MoE kernels. On the GPUMode TriMul task, K-Search achieves state-of-the-art performance on H100, reaching 1030us and surpassing both prior evolution and human-designed solutions.

The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic (O(N^2)) computational complexity that renders multi-user video conferencing applications unscalable. This paper proposes and evaluates a practical system-level framework designed to mitigate these critical bottlenecks. The proposed architecture incorporates a turn-taking mechanism to reduce computational complexity from quadratic to linear in multi-user scenarios, and a segmented processing protocol to manage inference latency for a perceptually real-time experience. We implement a proof-of-concept pipeline and conduct a rigorous performance analysis across a multi-tiered hardware setup, including commodity (NVIDIA RTX 4060), cloud (NVIDIA T4), and enterprise (NVIDIA A100) GPUs. Our objective evaluation demonstrates that the system achieves real-time throughput (τ< 1.0) on modern hardware. A subjective user study further validates the approach, showing that a predictable, initial processing delay is highly acceptable to users in exchange for a smooth, uninterrupted playback experience. The work presents a validated, end-to-end system design that offers a practical roadmap for deploying scalable, real-time generative AI applications in multilingual communication platforms.

Since Volta introduced Independent Thread Scheduling (ITS), NVIDIA GPUs have been widely assumed to handle warp divergence in a fixed manner. We test this assumption across Ampere, Hopper, and datacenter and consumer Blackwell GPUs, using pre-ITS Pascal as a baseline. Combining cycle-accurate microbenchmarks, hardware counters, and static analysis of compiler-generated SASS, we separate stable behavior from architectural change. Across all tested generations, divergent paths serialize linearly with the number of paths k, following T(k) approx sk with no super-linear reconvergence penalty. Warp execution efficiency falls as 32/k, the penalty is independent of occupancy, and predication removes the serialization cost. The same behavior appears on Pascal, showing that this programmer-visible cost model predates ITS. The compiler-emitted reconvergence machinery, however, has changed substantially. Pascal uses a per-warp SSY/SYNC instruction stack, whereas later generations use barrier-register instructions. Deferred reconvergence beyond the immediate post-dominator falls from 29 cases on Ampere to 2 on Blackwell. Blackwell also introduces a two-tier convergence-barrier classification, uniform-branch instructions, and explicit partial-mask warp synchronization, none of which appear on Ampere or Hopper. Controlled bit-flip experiments indicate that the new barrier class is a static compiler classification with no observable runtime effect in our tests. Thus, divergence retains a stable and predictable performance cost even as NVIDIA's control-flow ISA and reconvergence mechanisms continue to evolve.

GPU Confidential Computing (GPU-CC) now preserves GPU-local performance: on NVIDIA B300, BF16 matmul runs at 0.998x of non-confidential performance. Yet LLM serving under Intel TDX plus GPU-CC still loses 13-27% of throughput, and KV-cache restore latency can more than double. This paper studies that gap on two Blackwell platforms, RTX Pro 6000 and B300 HGX, and identifies its dominant cause: the confidential VM-GPU bridge, not GPU compute. We find that GPU-CC turns host/device movement into a serialized, high-setup-cost channel. Secure copies do not gain CUDA-stream concurrency within a context, asynchronous transfers block at the runtime boundary, and small crossings pay a fixed toll. This violates the assumptions of modern inference runtimes, where DMA is expected to be cheap, concurrent, and asynchronous. In vLLM dense decode, the gap closes around 44x-slower small alloc-and-copy operations; targeted patches reject alternative explanations. A scheduling flag recovers 57% of the gap, while a worker-thread drain recovers up to 92% in qualified high-concurrency runs. The same bridge model explains a +131% KV-restore penalty and a 34x model-load slowdown. Blackwell also changes the confidential tenancy unit. We qualify confidential multi-GPU NVSwitch tenants on B300, including 510 GB/s NVLink P2P inside a CVM and concurrent isolated tenants, and identify the remaining fabric-attestation gap for production confidential AI platforms.

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execution speed as the RL reward, CUDA-L2 automatically optimizes HGEMM kernels across 1,000 configurations. CUDA-L2 systematically outperforms major matmul baselines to date, from the widely-used {\it torch.matmul} to state-of-the-art Nvidia's closed-source libraries, i.e., {\it cuBLAS}, {\it cuBLASLt}. In offline mode, where kernels are executed consecutively without time intervals, CUDA-L2 yields +22.0\% over {\it torch.matmul} on average; +19.2\% over {\it cuBLAS} using the optimal layout configuration (normal-normal NN and transposed-normal TN); +16.8\% over {\it cuBLASLt-heuristic}, which queries {\it cuBLASLt} library and selects the algorithm based on the heuristic's suggestion; and +11.4\% over the most competitive {\it cuBLASLt-AutoTuning} model, which selects the fastest algorithm from up to 100 candidates from {\it cuBLASLt}'s suggestions. In server mode, where kernels are executed at random intervals simulating real-time inference, the speedups further increase to +28.7\%, +26.0\%, +22.4\%, and +15.9\% for {\it torch.matmul}, {\it cuBLAS}, {\it cuBLASLt-heuristic}, and {\it cuBLASLt-AutoTuning} respectively. CUDA-L2 shows that even the most performance-critical, heavily-optimized kernels like HGEMM can be improved through LLM-guided RL automation by systematically exploring configuration spaces at scales impractical for humans. Project and code can be found at github.com/deepreinforce-ai/CUDA-L2

Acceleration of graph applications on GPUs has found large interest due to the ubiquitous use of graph processing in various domains. The inherent irregularity in graph applications leads to several challenges for parallelization. A key challenge, which we address in this paper, is that of load-imbalance. If the work-assignment to threads uses node-based graph partitioning, it can result in skewed task-distribution, leading to poor load-balance. In contrast, if the work-assignment uses edge-based graph partitioning, the load-balancing is better, but the memory requirement is relatively higher. This makes it unsuitable for large graphs. In this work, we propose three techniques for improved load-balancing of graph applications on GPUs. Each technique brings in unique advantages, and a user may have to employ a specific technique based on the requirement. Using Breadth First Search and Single Source Shortest Paths as our processing kernels, we illustrate the effectiveness of each of the proposed techniques in comparison to the existing node-based and edge-based mechanisms.

Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losing this state after a GPU or communicator failure can discard minutes to hours of work, yet existing recovery mechanisms either restart the whole serving stack or require application-specific checkpoint logic inside every attention and runtime component. This paper argues that fault tolerance for such workloads needs a GPU-resident execution context: checkpoint hooks must run at device synchronization points, observe binary kernels that frameworks and libraries actually execute, and recover without putting the host CPU on the critical path. We present Concordia, a runtime that uses a device-resident persistent kernel as the substrate for fault-tolerant LLM inference. Concordia interposes on GPU module loading and supports PTX- and SASS-level instrumentation, allowing checkpoint and pause hooks to be inserted below framework code and library boundaries. For each registered LLM state region, Concordia JIT-compiles a specialized delta-checkpoint handler -- for example, a KV-block scanner, adapter-page scanner, or recovery applier -- and hot-swaps it into the persistent kernel's operator table. The persistent kernel consumes a lock-free ring buffer of compute, checkpoint, append-log, and recovery tasks, so the same always-on executor triggers dirty-page detection, stages deltas, and appends committed records to a CPU-visible log in CXL memory or host DRAM.

As large language models (LLMs) are increasingly deployed with highly heterogeneous workloads, chunked-prefill execution has emerged as a mainstream serving architecture. Balancing scheduling fairness and latency stability in such environments is critical; otherwise, severe head-of-line blocking and request starvation will degrade user experience. However, existing systems rely on rigid First-Come, First-Served (FCFS) policies and static token budgets, leading to fairness degradation and unpredictable latency jitter. To address these issues, we propose a fairness-aware and latency-controllable scheduling framework for chunked-prefill LLM engines. Specifically, we design a lightweight aging-based scheduling policy that dynamically calculates priorities using accumulated waiting time and remaining prefill work. Furthermore, we develop Latency-Prediction-Based Request Scheduling (LPRS) and Active Prefill Control (APC) to replace static budgets with target-time constraints and actively regulate prefill concurrency. We evaluated our scheduling framework on NVIDIA GPUs and Ascend accelerators using real-world workloads. Results show the aging policy reduces mean end-to-end latency by over 10\% compared to FCFS. Moreover, LPRS and APC significantly reduce P99 tail latency and suppress prefill fragmentation, confirming that the structural prefill control and the temporal latency constraints are fundamentally complementary. All codes have been released in Github.

Exponential increases in scientific experimental data are outstripping the rate of progress in silicon technology. As a result, heterogeneous combinations of architectures and process or device technologies are increasingly important to meet the computing demands of future scientific experiments. However, the complexity of heterogeneous computing systems requires systematic modeling to understand performance. We present a model which addresses this need by framing key aspects of data collection pipelines and constraints, and combines them with the important vectors of technology that shape alternatives, computing metrics that allow complex alternatives to be compared. For instance, a data collection pipeline may be characterized by parameters such as sensor sampling rates, amount of data collected, and the overall relevancy of retrieved samples. Alternatives to this pipeline are enabled by hardware development vectors including advancing CMOS, GPUs, neuromorphic computing, and edge computing. By calculating metrics for each alternative such as overall F1 score, power, hardware cost, and energy expended per relevant sample, this model allows alternate data collection systems to be rigorously compared. To demonstrate this model's capability, we apply it to the CMS experiment (and planned HL-LHC upgrade) to evaluate and compare the application of novel technologies in the data acquisition system (DAQ). We demonstrate that improvements to early stages in the DAQ are highly beneficial, greatly reducing the resources required at later stages of processing (such as a 60% power reduction) and increasing the amount of relevant data retrieved from the experiment per unit power (improving from 0.065 to 0.31 samples/kJ) However, we predict further advances will be required in order to meet overall power and cost constraints for the DAQ.

Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining computational efficiency. However, MoEs introduce several inference-time challenges, including load imbalance across experts and the additional routing computational overhead. To address these challenges and fully harness the benefits of MoE, a systematic evaluation of hardware acceleration techniques is essential. We present MoE-Inference-Bench, a comprehensive study to evaluate MoE performance across diverse scenarios. We analyze the impact of batch size, sequence length, and critical MoE hyperparameters such as FFN dimensions and number of experts on throughput. We evaluate several optimization techniques on Nvidia H100 GPUs, including pruning, Fused MoE operations, speculative decoding, quantization, and various parallelization strategies. Our evaluation includes MoEs from the Mixtral, DeepSeek, OLMoE and Qwen families. The results reveal performance differences across configurations and provide insights for the efficient deployment of MoEs.