[Feature] Add default and stable performance testing tools using the pytest framework #378
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
zzycode1005
commented
Nov 20, 2025
| BenchmarkModeType.STABLE_PREF, | ||
| BenchmarkModeType.DEFAULT_PERF, | ||
| ]: | ||
| stream = True |
Author
There was a problem hiding this comment.
Stream init missing when benchmark_mode not optional
zzycode1005
commented
Nov 25, 2025
| "Average time to first token latency: %.4f ms", avg_prefill_latency | ||
| ) | ||
|
|
||
| # 这里是list[list[float]]，要求的是这里所有float的平均（这里可能也会要求list[float]中去除前两个元素后，取所有请求per decode time的均值） |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Purpose
Added a new performance-testing tools supporting both stable and default performance.
Modifications
1、Supports TTFT metrics for all requests and for steady-state requests only.
2、Supports synthetic, multi-turn dialogue, and document QA datasets for performance testing.
Test