[Quantization] Fix Static FP8 Quantization #42775
fix
d61fcb97
fix style
e7538e06
SunMarc
approved these changes
on 2025-12-10
Update src/transformers/integrations/finegrained_fp8.py
9c9bfc30
fix
e71df508
style
de715607
MekkCyber
changed the title [Quantization] Upcast to FP8 for per tensor quantization [Quantization] Fix Static FP8 Quantization 86 days ago
Update src/transformers/integrations/finegrained_fp8.py
4739e205
Apply style fixes
b36adad1
MekkCyber
merged
15735a43
into main 86 days ago
MekkCyber
deleted the revert-fp8 branch 86 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub