PrototypeCommon
BenChaliah/NVFP4-on-4090-vLLM
AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVFP4 weights and keeps the entire decode path in FP8
- Owner
- BenChaliah (personal account)
- Stars
- Stars: 155
- Forks
- Forks: 7
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- gpu-accelerationgpu-computinginference-enginellmnvfp4nvidia-gpu
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- bertel2020/HA-HousekeeperStars: 155PythonPrototype
- silvermoong/stocking-texture-toolStars: 155PythonPrototype
- patch-gg/crowdbricksStars: 155PythonPrototype
- ramusus/kinopoiskpyStars: 155PythonPrototype
- Jonty/IdiocyStars: 155PythonPrototype
- CartoDB/carto-pythonStars: 155PythonPrototype