docs(benchmark): document warmup and add optional --num-warmup flag#138
Open
mvanhorn wants to merge 1 commit into
Open
docs(benchmark): document warmup and add optional --num-warmup flag#138mvanhorn wants to merge 1 commit into
mvanhorn wants to merge 1 commit into
Conversation
The benchmark warms up max(concurrency, 1) requests, and every README example uses --concurrency 1, so the documented default warms with a single request. Add an optional --num-warmup (default 8) and a README note so steady-state TPOT is not undersold. Fixes z-lab#135
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The benchmark warms up
max(concurrency, 1)requests before timing, and every README example uses--concurrency 1. So the documented default warms with a single request, which undersells steady-state TPOT (the reported cold-start numbers climb over the first several requests).Changes
--num-warmup(default 8) so the warmup count is decoupled from concurrency.Default behavior for users who pass
--concurrency >= 8is unchanged.Fixes #135
AI was used for assistance.