Remove residual quantization attribute from dequantized models #39373
fix: removing quantization trace attribute from dequantized model
820c30e8
add: test `to(dtype=torch.float16)` after dequantization
09ffc870
SunMarc
approved these changes
on 2025-07-15
SunMarc
merged
67f42928
into main 347 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub