Misc v0.7.0 Fixes#843
Merged
Merged
Conversation
The max_concurrency limit applies to all non-concurrency workloads. The current lmit is way too low and was kept that way because it is also the default for sweep. This chnage splits the two. Signed-off-by: Samuel Monson <smonson@redhat.com>
dbutenhof
previously approved these changes
Jun 24, 2026
Collaborator
|
Ping me when this is ready for review. I don't want it to auto-merge. |
Signed-off-by: Samuel Monson <smonson@redhat.com>
Signed-off-by: Samuel Monson <smonson@redhat.com>
jaredoconnell
approved these changes
Jun 25, 2026
Contributor
|
Queued — the merge queue status continues in this comment ↓. |
dbutenhof
approved these changes
Jun 25, 2026
dbutenhof
left a comment
Collaborator
There was a problem hiding this comment.
And it stops when it should? Yea!
Contributor
Merge Queue Status
This pull request spent 3 minutes 41 seconds in the queue, including 3 minutes 22 seconds running CI. Required conditions to merge
|
34 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes a couple smaller issues.
Details
1. Bump max_concurrency
See more details in the commit description, but the primary reason to bump it now is because the replay profile is also subjected to it.
2. Drop the max-request modifier from replay
This code never made sense to have and was just a holdover from when the profile was responsible for trace timing. There is an automatic constraint that ends the benchmark when the dataset is exhausted that serves the same purpose.
Test Plan
For replays a longer dataset can be provided and limited to a smaller number of samples:
guidellm run \ --backend kind=openai_http,target=https://localhost:8000 \ --profile kind=replay,time_scale=0.01 \ --data-loader kind=pytorch,samples=30 \ --data kind=trace_synthetic,path=./data.jsonlUse of AI
git log
commit 78b4014
Author: Samuel Monson smonson@redhat.com
Date: Wed Jun 24 13:52:57 2026 -0400
commit 850e8f3
Author: Samuel Monson smonson@redhat.com
Date: Thu Jun 25 15:07:50 2026 -0400
commit 522b457
Author: Samuel Monson smonson@redhat.com
Date: Thu Jun 25 15:23:31 2026 -0400
Signed-off-by: Samuel Monson smonson@redhat.com