Merged
Conversation
seanshi-scale
requested review from
song-william,
squeakymouse and
yunfeng-scale
| / (elapsed * avg_completion_time / (avg_prefill_time + avg_completion_time)) | ||
| / concurrency, | ||
| "avg_request_throughput": n / elapsed, | ||
| "avg_inter_token_latency": sum(inter_token_latency) / n, |
Contributor
There was a problem hiding this comment.
what about percentiles for this? also i wonder if we can have percentiled numbers for throughput numbers?
Member
There was a problem hiding this comment.
+1 I think throughput is more easily interpretable to users?
Contributor
Author
There was a problem hiding this comment.
I've added percentiles for inter-token latency + time to first token, not sure how to get percentiles for throughput (since I think it's a single value for the entire test)
yunfeng-scale
approved these changes
Jan 31, 2024
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request Summary
Add some changes to the benchmark script to be more detailed
Test Plan and Usage Guide
Ran benchmark script locally