64d231f384
* add flux support * avoid build failures in non-CUDA environments * fix schnell support * add k quants support * add support for applying lora to quantized tensors * add inplace conversion support for f8_e4m3 (#359) in the same way it is done for bf16 like how bf16 converts losslessly to fp32, f8_e4m3 converts losslessly to fp16 * add xlabs flux comfy converted lora support * update docs --------- Co-authored-by: Erik Scholz <Green-Sky@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| flux1-dev-q2_k.png | ||
| flux1-dev-q3_k.png | ||
| flux1-dev-q4_0.png | ||
| flux1-dev-q8_0 with lora.png | ||
| flux1-dev-q8_0.png | ||
| flux1-schnell-q8_0.png | ||
