Illustration: the project’s public image, pixelated by RepoMasters. Credits
BetaRare

zhihu/ZhiLight

A highly optimized LLM inference acceleration engine for Llama and its variants.

Owner
zhihu (organization)
Stars
Stars: 906
Forks
Forks: 105
Language
C++
License
Apache-2.0
Created
2024
Topics
inference-enginellmcudagptllamallm-servingpytorchllm-inferencemodel-servingdeepseek-r1
Tier
Beta (700 to 1,999 ★) What this tier means
View on GitHub

More repos by zhihu

All 13 repos by zhihu

Nearby in C++

All C++ repos