friedpotato04/CUDA-L2

🚀 Optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels using reinforcement learning, surpassing cuBLAS and other benchmarks with superior performance.

22
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Cuda

License

MIT

Category

llm-cuda-optimization

Last pushed

Mar 13, 2026

Commits (30d)

0

GitHub
LLM CUDA Optimization · 27 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/friedpotato04/CUDA-L2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

ggml-org/ggml

Tensor library for machine learning

68

onnx/ir-py

Efficient in-memory representation for ONNX, in Python

55

SandAI-org/MagiCompiler

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

49

bytedance/lightseq

LightSeq: A High Performance Library for Sequence Processing and Generation

46

R-D-BioTech-Alaska/Qelm

Qelm - Quantum Enhanced Language Model

45

Explore LLM Tools

All categories Trending LLM Tool directory Insights