Keep lm-head quantization scales for nemotron --mtp export - #26903
Merged
Conversation
Signed-off-by: ynankani <ynankani@nvidia.com>
ruixiang63
approved these changes
Aug 11, 2026
ynankani
marked this pull request as ready for review
August 11, 2026 12:38
Member
|
@CISC Could you take a look? This is must for NVFP4 quantized model. |
CISC
approved these changes
Aug 11, 2026
huaxel
pushed a commit
to huaxel/CachyLLama
that referenced
this pull request
Aug 12, 2026
…g#26903) Signed-off-by: ynankani <ynankani@nvidia.com>
Ooooze
pushed a commit
to AtomicBot-ai/atomic-llama-cpp-turboquant-nightly
that referenced
this pull request
Aug 14, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
This PR handles the --mtp export for the Nemotron Nano model with quantized lm_head. Performance is not yet optimal and similar to #26725 this PR also depends on PR #26623 being merged first.
I tested this PR on the top of PR #26623, and the performance looks good.
Additional information
Requirements