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.

Date Created 2024-08-05 (3 months ago)

Commits 64 (last one 25 days ago)

Stargazers 201 (1 this week)

Watchers 6 (0 this week)

Forks 20

License apache-2.0

Ranking

RepositoryStats indexes 579,555 repositories, of these aredden/flux-fp8-api is ranked #177,082 (69th percentile) for total stargazers, and #296,754 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #31,302/115,123.

aredden/flux-fp8-api is also tagged with popular topics, for these it's ranked: pytorch (#2,429/5914)

Other Information

aredden/flux-fp8-api has Github issues enabled, there are 13 open issues and 12 closed issues.

All Topics

fp8 flux pytorch diffusion quantization fast-inference

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

64 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The only known language in this repository is Python

updated: 2024-11-05 @ 06:53pm, id: 838518770 / R_kgDOMfrH8g