AlphaUncommon
aredden/flux-fp8-api
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
- Owner
- aredden (personal account)
- Stars
- Stars: 285
- Forks
- Forks: 34
- Language
- Python
- License
- Apache-2.0
- Created
- 2024
- Topics
- diffusionfast-inferencefluxfp8pytorchquantization
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by aredden
All 2 repos by aredden- aredden/electron-G14ControlStars: 206TypeScriptPrototype
Nearby in Python
All Python repos- OmooLab/AnyImageStars: 285PythonAlpha
- BinceQu/RoboHarnessStars: 285PythonAlpha
- Wunsch2048/codex-bailong-desktop-petStars: 285PythonAlpha
- Arachnid/bloggartStars: 285PythonAlpha
- batiste/django-page-cmsStars: 285PythonAlpha
- eddorre/SublimeERBStars: 285PythonAlpha