francois141/ptx_gym

KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

A benchmark of real-world DL kernel problems

A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch

Multi-Level Triton Runner supporting Python, IR, PTX, AMDGCN, cubin and hasco.

kernelbench.com — GPU kernel engineering benchmarks for autonomous LLM coding agents. v3 archive + v-hard latest.

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

AgentKernelArena is a platform for evaluating and training AI agents for GPU kernel optimization, combining realistic tasks, correctness validation, and performance-based rewards for reinforcement learning.