GitHub · C++
jmaczan/tiny-vllm
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
- Stars
- 1,207
- Forks
- 107
- Stars gained in 24 hours
- +46
- Forks gained in 24 hours
- +6
Topics: ai, hpc, llm, llm-inference, vllm, tiny-vllm, cpp, cuda, pagedattention, attention
Latest data point: Nov 22, 2026 · 1,207 stars · 107 forks