add random concurrent workload template for inference-perf#635
Merged
namasl merged 2 commits intollm-d:mainfrom Feb 2, 2026
Merged
add random concurrent workload template for inference-perf#635namasl merged 2 commits intollm-d:mainfrom
namasl merged 2 commits intollm-d:mainfrom
Conversation
namasl
requested changes
Feb 1, 2026
Collaborator
namasl
left a comment
namasl
left a comment
There was a problem hiding this comment.
Profiles prefixed with sanity_ tend to be small benchmarks that run quickly (sanity checks, used for tests and CI). Drop the prefix, then it looks good to me.
Collaborator
|
+1 on @namasl comment |
Signed-off-by: Xia Hua <huaxi@google.com>
Contributor
Author
|
SG, rename it to |
namasl
approved these changes
Feb 2, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
introduces a new inference-perf workload profile for sanity testing with concurrent users.
The sanity_random_concurrent profile is designed to test the stability and performance of the llm-d stack under increasing load. It consists of 4 stages, starting with 1 concurrent user and scaling up to 8.