llama.cpp
convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8)
#32476
Merged

convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) #32476

am17an
am17an convert : fix FP8 n-gram table export for qwen4exp
38d3ed7f
am17an convert : dequantize block-scaled FP8 weight_scale_inv in ModelOpt ch…
a5c7e9ef
am17an am17an marked this pull request as ready for review 2 days ago
am17an am17an requested a review from ggerganov ggerganov 2 days ago
am17an am17an requested a review 2 days ago
am17an am17an requested a review from CISC CISC 2 days ago
am17an am17an requested a review 2 days ago
github-actions github-actions added model
github-actions github-actions added testing
github-actions github-actions added conversion
CISC
CISC approved these changes on 2026-11-17
ngxson
ngxson approved these changes on 2026-11-17
am17an am17an merged d3064fdd into master 2 days ago
ORippler
CISC

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone