Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@ This is an unavoidable double quantization due to the release state of Ideogram4
|
|
| 2 |
|
| 3 |
The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
|
| 4 |
|
| 5 |
-
For use with https://github.com/BobJohnson24/ComfyUI-INT8-Fast
|
| 6 |
|
| 7 |
Speed is 1.78x faster(2.03s/it) than FP8(3.62s/it) on my 3090, without compile.
|
| 8 |
|
|
|
|
| 2 |
|
| 3 |
The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
|
| 4 |
|
| 5 |
+
For use in ComfyUI with https://github.com/BobJohnson24/ComfyUI-INT8-Fast
|
| 6 |
|
| 7 |
Speed is 1.78x faster(2.03s/it) than FP8(3.62s/it) on my 3090, without compile.
|
| 8 |
|