Skip to content

Conversation

@liyonghua0910
Copy link
Collaborator

@liyonghua0910 liyonghua0910 commented Nov 3, 2025

Motivation

修复 #4693 遗留的问题:为了修复 v1 调度下 PD 分离的启动问题, 将 step_shm_value 修改成了通过 shared_memory_exists() 判断是否要临时创建该信号量。但实测这种写法会在压测途中挂掉。

Modifications

Worker 在 v0 下不需要创建该信号量,在 v1 下不应该去读取该信号量:

if not envs.ENABLE_V1_KVCACHE_SCHEDULER and self.scheduler_config.splitwise_role == "prefill":
    step_shm_value = IPCSignal(..., create=False)

Usage or Command

Accuracy Tests

Checklist

  • Add at least a tag in the PR title.
    • Tag list: [[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]]
    • You can add new tags based on the PR content, but the semantics must be clear.
  • Format your code, run pre-commit before commit.
  • Add unit tests. Please write the reason in this PR if no unit tests.
  • Provide accuracy results.
  • If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

@paddle-bot
Copy link

paddle-bot bot commented Nov 3, 2025

Thanks for your contribution!

Copy link
Collaborator

@K11OntheBoat K11OntheBoat left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 1b61d62 into PaddlePaddle:develop Nov 4, 2025
21 of 23 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants