[Cherry-Pick][RL] Support Rollout Routing Replay #5166
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! |
gongshaotian
changed the title
gongshaotian
commented
Dec 1, 2025
| moba_attention_config = self.create_moba_attention_config() | ||
| eplb_cfg = self.create_eplb_config() | ||
| routing_replay_config = self.create_routing_repaly_config() | ||
| print("after create {routing_replay_config}") |
Collaborator
Author
There was a problem hiding this comment.
delete debug code
gongshaotian
commented
Dec 1, 2025
|
|
||
| @abstractmethod | ||
| def apply_ep_decode( | ||
| self, |
Collaborator
Author
There was a problem hiding this comment.
为啥 ep decode 没加 hook
gongshaotian
commented
Dec 1, 2025
Collaborator
Author
There was a problem hiding this comment.
develop 分支的 xpu backend 迁移到哪里了？
8 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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
In RL training tasks, we have enabled recording of routing information during the inference process and directly utilized the experts selected during inference in the training process to alleviate the consistency issue between training and inference.
Modifications
Add
RoutingReplayManagerandRoutingStoreclass to support routing replayRoutingStore: The client used for interacting with Routing Store has two routing storage modes based on File System and RDMA(WIP).RoutingReplayManager: Implement request level routing table management within FastDeploy.Usage or Command
Add a startup switch for route replay：
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.