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.
Npueval: Optimizing npu kernels with llms and open source compilers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
A two-stage agent skill system enables autonomous end-to-end deployment of eight decoder-only LLMs on AMD XDNA 2 NPU with numerical correctness in 0.5-4 hours each, generalizing from a human-guided Llama-3.2-1B reference.
Presents Metal-Sci benchmark and harness for evolutionary LLM kernel search on Apple Silicon Metal, reporting in-distribution speedups up to 10.7x and using held-out gate scoring as oversight.
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.
-
From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs
A two-stage agent skill system enables autonomous end-to-end deployment of eight decoder-only LLMs on AMD XDNA 2 NPU with numerical correctness in 0.5-4 hours each, generalizing from a human-guided Llama-3.2-1B reference.
-
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
Presents Metal-Sci benchmark and harness for evolutionary LLM kernel search on Apple Silicon Metal, reporting in-distribution speedups up to 10.7x and using held-out gate scoring as oversight.