NVIDIA / compute-evalLinks
Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Large Language Models.
☆65Updated 3 months ago
Alternatives and similar repositories for compute-eval
Users that are interested in compute-eval are comparing it to the libraries listed below
Sorting:
- ☆234Updated last week
- Applied AI experiments and examples for PyTorch☆294Updated 3 weeks ago
- Fast low-bit matmul kernels in Triton☆365Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆311Updated this week
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆69Updated last month
- extensible collectives library in triton☆87Updated 5 months ago
- Cataloging released Triton kernels.☆257Updated last week
- TritonParse: A Compiler Tracer, Visualizer, and mini-Reproducer Generator(WIP) for Triton Kernels☆150Updated this week
- ☆88Updated 10 months ago
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆92Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆221Updated this week
- kernels, of the mega variety☆488Updated 3 months ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆566Updated 3 weeks ago
- ☆118Updated 6 months ago
- ☆43Updated last week
- Collection of kernels written in Triton language☆154Updated 5 months ago
- An experimental CPU backend for Triton☆148Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆519Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆299Updated this week
- Fastest kernels written from scratch☆343Updated 5 months ago
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆354Updated this week
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆221Updated 4 months ago
- Perplexity GPU Kernels☆461Updated last month
- ☆231Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆353Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- AMD RAD's experimental RMA library for Triton.☆63Updated this week
- ☆116Updated 8 months ago
- High-Performance SGEMM on CUDA devices☆101Updated 7 months ago
- ☆42Updated this week