[fix] Fix qwen3.5 MoE vp_stage propagation under VPP#112
Open
none0663 wants to merge 1 commit intoISEEKYAN:mainfrom
Open
[fix] Fix qwen3.5 MoE vp_stage propagation under VPP#112none0663 wants to merge 1 commit intoISEEKYAN:mainfrom
none0663 wants to merge 1 commit intoISEEKYAN:mainfrom
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pass vp_stage from Qwen3_5VlBaseBridge provider to Qwen3_5VLModel.
Add vp_stage arg in Qwen3_5VLModel and forward to GPTModel only when the current Megatron version supports it.
Keep backward compatibility for older Megatron versions that may do not accept vp_stage in GPTModel.init.