llama.cpp
Keep lm-head quantization scales for nemotron --mtp export
#26903

Merged

Keep lm-head quantization scales for nemotron --mtp export #26903

CISC merged 1 commit into ggml-org:master from ynankani:ynankani/nemotron_nvfp4_mtp

Keep quantization scales for nemotron --mtp export

e74eded3

github-actions added conversion

ruixiang63 approved these changes on 2026-08-11

ynankani marked this pull request as ready for review 8 days ago

ynankani requested a review from

CISC 8 days ago

CISC approved these changes on 2026-08-11

CISC merged 5d16e81d into master 8 days ago

Reviewers

CISC

ruixiang63

Assignees

No one assigned

Labels

conversion

Milestone

No milestone