Add MixedPrecisionOps compatible fp8mixed qwen_image_edit_2509 with sensitive layers kept in high precision and using full_precision_matrix_mult (#11)

- Add MixedPrecisionOps compatible fp8mixed qwen_image_edit_2509 with sensitive layers kept in high precision and using full_precision_matrix_mult (2c425ab26567be2f69c1eaca985a13d7a0e68e4e)


Co-authored-by: Silver <silveroxides@users.noreply.huggingface.co> (batch 1/1)
This commit is contained in:
systemd
2025-12-20 16:25:55 +00:00
parent 55b3e6e2ba
commit 6af71b2462
2 changed files with 6 additions and 1 deletions

View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c742e8c584c11f65d846816b334d2c25a89e0a196d2790a813c6bf943e40a492
size 20533579421