FastKernels is a production-aligned benchmark covering 96.2% of HuggingFace Transformers that reveals state-of-the-art kernel agents deliver at most 0.94x aggregate speedup.
Cudaforge: An agent framework with hardware feedback for cuda kernel optimization
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 11roles
background 1polarities
background 1representative citing papers
CUDAHercules benchmark demonstrates that leading LLMs generate functional CUDA code but fail to recover expert-level optimization strategies needed for peak performance on Ampere, Hopper, and Blackwell GPUs.
Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
SpecGen introduces speculative generation to fork non-reasoning kernel candidates during LLM reasoning traces, enabling early termination and parallel profiling to reduce end-to-end optimization time on H200 GPUs.
Deopt-Reopt workflow for LLM-based C++ to CUDA porting shows mixed performance gains over direct translation depending on kernel, model, and success rate, with no universal benefit.
Kernel-Smith combines evolutionary search with RL post-training to generate optimized GPU kernels, achieving SOTA speedups on KernelBench that beat Gemini-3.0-pro and Claude-4.6-opus on NVIDIA Triton and generalize to MetaX MACA.
Sol Video Inference Engine uses parallel skill agents to optimize cache, sparse attention, token pruning, quantization, and kernel fusion, delivering over 2x end-to-end acceleration with near-lossless quality on three video models.
HTAM builds a Hierarchical Transition Graph to organize coarse global directions and detailed local strategies for guiding LLM-based CUDA kernel optimization, improving results on KernelBench.
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
AscendOptimizer combines kernel rewinding for reusable experience with evolutionary search on hardware feedback to optimize Ascend NPU operators, delivering 1.21x geometric-mean speedup and faster performance on 53.47% of 101 tested operators versus baseline.
citing papers explorer
-
FastKernels: Benchmarking GPU Kernel Generation in Production
FastKernels is a production-aligned benchmark covering 96.2% of HuggingFace Transformers that reveals state-of-the-art kernel agents deliver at most 0.94x aggregate speedup.
-
CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
CUDAHercules benchmark demonstrates that leading LLMs generate functional CUDA code but fail to recover expert-level optimization strategies needed for peak performance on Ampere, Hopper, and Blackwell GPUs.
-
Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
-
SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation
SpecGen introduces speculative generation to fork non-reasoning kernel candidates during LLM reasoning traces, enabling early termination and parallel profiling to reduce end-to-end optimization time on H200 GPUs.
-
LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization
Deopt-Reopt workflow for LLM-based C++ to CUDA porting shows mixed performance gains over direct translation depending on kernel, model, and success rate, with no universal benefit.
-
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
Kernel-Smith combines evolutionary search with RL post-training to generate optimized GPU kernels, achieving SOTA speedups on KernelBench that beat Gemini-3.0-pro and Claude-4.6-opus on NVIDIA Triton and generalize to MetaX MACA.
-
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Sol Video Inference Engine uses parallel skill agents to optimize cache, sparse attention, token pruning, quantization, and kernel fusion, delivering over 2x end-to-end acceleration with near-lossless quality on three video models.
-
HTAM: Hierarchical Transition-Attended Memory for Operator Optimization
HTAM builds a Hierarchical Transition Graph to organize coarse global directions and detailed local strategies for guiding LLM-based CUDA kernel optimization, improving results on KernelBench.
-
KEET: Explaining Performance of GPU Kernels Using LLM Agents
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
-
AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
AscendOptimizer combines kernel rewinding for reusable experience with evolutionary search on hardware feedback to optimize Ascend NPU operators, delivering 1.21x geometric-mean speedup and faster performance on 53.47% of 101 tested operators versus baseline.
- Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization