Skip to content

[BugFix] Fix ascend scheduler bugs.#822

Merged
ganyi1996ppo merged 1 commit intovllm-project:mainfrom
whx-sjtu:fix_ascend_scheduler
May 12, 2025
Merged

[BugFix] Fix ascend scheduler bugs.#822
ganyi1996ppo merged 1 commit intovllm-project:mainfrom
whx-sjtu:fix_ascend_scheduler

Conversation

@whx-sjtu
Copy link
Copy Markdown
Collaborator

This PR fixes two bugs in AscendScheduler:

  1. When running with high concurrency, the length of running queue may exceed the limit of max_num_seqs
  2. When some requests are prempted and recomputing is activated, the logic of computing new tokens is wrong.

Signed-off-by: whx-sjtu <2952154980@qq.com>
@wangxiyuan
Copy link
Copy Markdown
Collaborator

@ganyi1996ppo

@ganyi1996ppo ganyi1996ppo merged commit 5998704 into vllm-project:main May 12, 2025
14 checks passed
@whx-sjtu whx-sjtu deleted the fix_ascend_scheduler branch July 9, 2025 07:10
chopper0126 pushed a commit to chopper0126/vllm-ascend that referenced this pull request Oct 16, 2025
This PR fixes two bugs in AscendScheduler:
1. When running with high concurrency, the length of running queue may
exceed the limit of max_num_seqs
2. When some requests are prempted and recomputing is activated, the
logic of computing new tokens is wrong.

Signed-off-by: whx-sjtu <2952154980@qq.com>
Angazenn pushed a commit to Angazenn/vllm-ascend that referenced this pull request Oct 21, 2025
This PR fixes two bugs in AscendScheduler:
1. When running with high concurrency, the length of running queue may
exceed the limit of max_num_seqs
2. When some requests are prempted and recomputing is activated, the
logic of computing new tokens is wrong.

Signed-off-by: whx-sjtu <2952154980@qq.com>
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