BetaRare
jmaczan/tiny-vllm
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
- Owner
- jmaczan (personal account)
- Stars
- Stars: 1,180
- Forks
- Forks: 102
- Language
- C++
- License
- Apache-2.0
- Created
- 2026
- Topics
- aihpcllmllm-inferencevllmtiny-vllmcppcudapagedattentionattention
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by jmaczan
All 3 repos by jmaczan- jmaczan/bulma-helpersStars: 281CSSAlpha
- jmaczan/gdansk-aiStars: 197TypeScriptPrototype
Nearby in C++
All C++ repos- Diegiwg/PrismLauncher-CrackedStars: 1,182C++Beta
- madmann91/bvhStars: 1,180C++Beta
- TheForceEngine/TheForceEngineStars: 1,180C++Beta
- davmac314/dinitStars: 1,179C++Beta
- retronx-team/sys-clkStars: 1,179C++Beta