Enabled Qwen2-MoE Tensor Parallelism (TP) inference #6551
Conversation
This file contains 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
|
Hi @Yejing-Lai , do you want to provide some comments on this PR for Qwen2-MoE AutoTP support? |
|
Could you try to modify this line if it can meet your needs? https://github.com/microsoft/DeepSpeed/blob/master/deepspeed/module_inject/auto_tp.py#L336 |
23 tasks
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Outdated suggestions cannot be applied.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.
Modified _replace_module in auto_tp.py :
The modification keeps the layers 'shared_expert_gate' and 'gate' in qwen2-moe the original type torch.nn.Linear and not changes them into LinearLayer. In this way, their weights will not be split into multiple HPU/GPU cards. Then the qwen2-moe can run on multiple HPU/GPU cards.
Since the weights of 'gate' are not split into multiple HPU/GPU cards, all gather operations are not needed, which may improve performance.