Skip to content

[benchmark] Update warmup logic for min_tokens and max_tokens - #8110

Merged
ZhangYulongg merged 1 commit into
developfrom
ZhangYulongg-patch-1
Aug 21, 2026
Merged

[benchmark] Update warmup logic for min_tokens and max_tokens#8110
ZhangYulongg merged 1 commit into
developfrom
ZhangYulongg-patch-1

Conversation

@ZhangYulongg

Copy link
Copy Markdown
Collaborator

Motivation

warmup优化,兼容固定输出长度场景

Modifications

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.

Adjust warmup parameters to ensure min_tokens converges with max_tokens.
@ZhangYulongg
ZhangYulongg merged commit 295ad39 into develop Aug 21, 2026
41 of 42 checks passed
@ZhangYulongg
ZhangYulongg deleted the ZhangYulongg-patch-1 branch August 21, 2026 10:28
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.

1 participant