Hybrid MoE, combining EP and TP#2001
Open
zhangamy-crypto wants to merge 7 commits intovllm-project:mainfrom
Open
Hybrid MoE, combining EP and TP#2001zhangamy-crypto wants to merge 7 commits intovllm-project:mainfrom
zhangamy-crypto wants to merge 7 commits intovllm-project:mainfrom
Conversation
…ps expert sharding to attention's DP sharding.
zhangamy-crypto
requested review from
bzgoogle,
gpolovets1,
jrplatin,
kyuyeunk,
vanbasten23 and
vipannalla
as code owners
Signed-off-by: zhangamy-crypto <zhangamy@google.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Add hybrid expert and tensor parallelism support in MoE; currently maps expert sharding to attention's DP sharding.
Tests
Tested on Qwen3 Coder and for prefill, improved throughput and latency.