jmaczan/tiny-vllm

GitHub

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

C++993 stars69 forksApache-2.0

ai attention batching course cpp cuda hpc inference llm llm-inference pagedattention tiny-vllm vllm

Momentum

jmaczan/tiny-vllm has 993 GitHub stars.

It currently ranks #38940 daily, #39077 weekly, #40025 monthly by momentum on Trending Repos; its best-ever rank is #3456.

Rankings

PeriodRankScore

Daily

#389400.0

Weekly

#390770.0

Monthly

#400250.0

How scoring works

Engagement

Total stars

Daily new stars

Embeds

Best rank #3456

Format

Markdown

[![jmaczan/tiny-vllm badge](https://trending-repos.com/badge/jmaczan/tiny-vllm.svg?v=3)](https://trending-repos.com/repositories/jmaczan/tiny-vllm?utm_source=github&utm_medium=badge)

jmaczan/tiny-vllm

Momentum

Rankings

Engagement

Similar trending repositories

Embeds

jmaczan/tiny-vllm

Momentum

Rankings

Engagement

Similar trending repositories

Embeds