AlphaUncommon
interestingLSY/swiftLLM
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
- Owner
- interestingLSY (personal account)
- Stars
- Stars: 363
- Forks
- Forks: 43
- Language
- Python
- License
- Apache-2.0
- Created
- 2024
- Topics
- transformertransformerscudainferenceinference-enginepytorchgptllamallmllm-inference
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by interestingLSY
All 2 repos by interestingLSY- interestingLSY/CUDA-From-Correctness-To-Performance-CodeStars: 187C++Prototype
Nearby in Python
All Python repos- ziplab/TriSplatStars: 363PythonAlpha
- caipeng328/TeleOCRStars: 363PythonAlpha
- MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFoldStars: 363PythonAlpha
- albertz/PyCParserStars: 363PythonAlpha
- openaddresses/pyesridumpStars: 363PythonAlpha
- psolin/cleancoStars: 363PythonAlpha