LessUp/llm-speed

CUDA Kernel Library for LLM Inference: FlashAttention, HGEMM, Tensor Core GEMM with pybind11 Bindings | LLM 推理加速 CUDA Kernel 库：FlashAttention、HGEMM、Tensor Core GEMM，含 pybind11 Python 绑定

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

MIT

Category

llm-quantization-techniques

Last pushed

Mar 13, 2026

Commits (30d)

0

GitHub
Llm Quantization Techniques · 22 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/LessUp/llm-speed"

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

Higher-rated alternatives

bitsandbytes-foundation/bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

77

intel/neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model...

74

dropbox/hqq

Official implementation of Half-Quadratic Quantization (HQQ)

54

OpenGVLab/OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

49

Hsu1023/DuQuant

[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger...

40

Explore Transformer Models

All categories Trending Transformer directory Insights