search

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.
Apache License 2.0
210 stars 22 forks source link

add h100 #11

Closed ClashLuke closed 2 months ago

aredden commented 2 months ago

Awesome! Thanks 😄