llama.cpp
convert : avoid dequantizing mxfp4 for GPT-OSS
#16756
Merged

convert : avoid dequantizing mxfp4 for GPT-OSS #16756

compilade
compilade convert : avoid dequantizing mxfp4 for GPT-OSS
d7f794ea
compilade compilade requested a review from CISC CISC 236 days ago
compilade compilade added bugfix
compilade compilade added python
danbev
danbev approved these changes on 2025-10-24
ngxson
ngxson approved these changes on 2025-10-24
compilade compilade merged 5cca2542 into master 235 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone