[XPU] [Optimization] [EP] EP communication optimization. #5145
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
|
Thanks for your contribution! |
zhupengyang
reviewed
Nov 20, 2025
| self.group = group | ||
| self.num_local_experts = num_experts // ep_size | ||
| self.deepep_engine = None | ||
| self.deepep_engine = None # deepep_engine只调用dispatch, combine |
Comment on lines
+932
to
+974
| if_only_decode = self.only_decode() | ||
| if ( | ||
| self.fd_config.scheduler_config.splitwise_role == "mixed" | ||
| ): # 集中式场景，phase默认初始化为prefill, 推理运行时不同类型的batch能够在此处实现phase切换 | ||
| self.fd_config.model_config.moe_phase.phase = "decode" if if_only_decode else "prefill" | ||
|
|
Collaborator
There was a problem hiding this comment.
only_decoder=self.forward_meta.len_info_cpu[0]<=0
| permute_input, | ||
| token_nums_per_expert, | ||
| valid_token_num, | ||
| max(1, valid_token_num), # 确保空跑时也不为0 |
Collaborator
There was a problem hiding this comment.
在算子moe_expert_ffn中支持valid_token_num=0的情况
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## develop #5145 +/- ##
==========================================
Coverage ? 57.86%
==========================================
Files ? 317
Lines ? 38315
Branches ? 5727
==========================================
Hits ? 22171
Misses ? 14380
Partials ? 1764
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Motivation
Implement low-latency version communication operators for pure D requests, and high-throughput version communication operators for P requests in centralized inference scenarios.
Modifications
Usage or Command
export MOE_FFN_USE_DENSE_INPUT=1
Accuracy Tests
Checklist
[FDConfig],[APIServer],[Engine],[Scheduler],[PD Disaggregation],[Executor],[Graph Optimization],[Speculative Decoding],[RL],[Models],[Quantization],[Loader],[OP],[KVCache],[DataProcessor],[BugFix],[Docs],[CI],[Optimization],[Feature],[Benchmark],[Others],[XPU],[HPU],[GCU],[DCU],[Iluvatar],[Metax]]pre-commitbefore commit.releasebranch, make sure the PR has been submitted to thedevelopbranch, then cherry-pick it to thereleasebranch with the[Cherry-Pick]PR tag.