[Jax][Deepseek] Updated sharding scales to align with GMM_TP settings.#1865
Open
gpolovets1 wants to merge 1 commit intomainfrom
Open
[Jax][Deepseek] Updated sharding scales to align with GMM_TP settings.#1865gpolovets1 wants to merge 1 commit intomainfrom
gpolovets1 wants to merge 1 commit intomainfrom
Conversation
Signed-off-by: George Polovets <gpolovets@gmail.com>
DescriptionStart with a short description of what the PR does and how this is a change from The rest of the description includes relevant details and context, examples:
If the change fixes a Github issue, please include a link, e.g.,: TestsPlease describe how you tested this change, and include any instructions and/or ChecklistBefore submitting this PR, please make sure:
|
lk-chen
approved these changes
Mar 5, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Fixed scale shardings to properly work with gmm_TP and in the case of per-channel quantization (which is needed for gmm_v2.py as of 3/4/26).
Tests
Please describe how you tested this change, and include any instructions and/or
commands to reproduce.
Checklist
Before submitting this PR, please make sure: