AlphaUncommon
localai-org/vllm.cpp
a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)
- Owner
- localai-org (organization)
- Stars
- Stars: 474
- Forks
- Forks: 58
- Language
- C++
- License
- Apache-2.0
- Created
- 2026
- Topics
- mlxvllmcpp20llmcontinous-batchingpaged-attentionradixattention
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by localai-org
All 10 repos by localai-org- localai-org/depth-anything.cppStars: 1,136C++Beta
- localai-org/kimodo.cppStars: 946C++Beta
- localai-org/apex-quantStars: 482ShellAlpha
- localai-org/motion-bricks.cppStars: 346C++Alpha
- localai-org/privacy-filter.cppStars: 308C++Alpha
- localai-org/LocalVQEStars: 246C++Prototype
Nearby in C++
All C++ repos- SamoZ256/hydraStars: 474C++Alpha
- M4THYOU/TokenDaggerStars: 474C++Alpha
- UrbanCircles/scribeStars: 474C++Alpha
- pyroscope/rtorrent-psStars: 474C++Alpha
- DentonW/DevILStars: 474C++Alpha
- dmtcp/dmtcpStars: 474C++Alpha