[DeepSeek] Move seqlen from model config to setup_symm_mem
#1017
Conversation
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
facebook-github-bot
added
the
CLA Signed
lessw2020
approved these changes
Mar 25, 2025
There was a problem hiding this comment.
lgtm!
One note - the changes in symm_mem_recipes are assumed but not present here in this PR as a change nor in main? (I had to hand add those to get things to run).
verified changes as well:
Creating model stage 0 of 2
Creating model stage 1 of 2
Creating model stage 0 of 2
Creating model stage 1 of 2
EP rank [0]: Created Symmetric Memory for MoE
EP rank [1]: Created Symmetric Memory for MoE
EP rank [1]: Created Symmetric Memory for MoE
EP rank [0]: Created Symmetric Memory for MoE
NCCL version 2.25.1+cuda12.2
NCCL version 2.25.1+cuda12.2
NCCL version 2.25.1+cuda12.2
<｜begin▁of▁sentence｜>You are a helpful assistant.
User: What is 2+2?
Assistant: 2 + 2 equals 4.<｜end▁of▁sentence｜>
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Outdated suggestions cannot be applied.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.
Just a UI change. The seqlen is mainly used in setting up symm mem. That's why we move it out of model config.