Added rampup to constant rate type#549
Merged
jaredoconnell merged 2 commits intovllm-project:mainfrom Jan 23, 2026
Merged
Conversation
7 tasks
Generated-by: Cursor AI Signed-off-by: Jared O'Connell <joconnel@redhat.com>
Signed-off-by: Jared O'Connell <joconnel@redhat.com>
d895b07 to
eb6a803
Compare
openclaw-architect bot
pushed a commit
to tylertitsworth/skills
that referenced
this pull request
Mar 3, 2026
…ring Configurations section - --rampup applies only to constant rate-type benchmarks per v0.5.3 changelog and implementing PR (vllm-project/guidellm#549); remove incorrect claim that it works with throughput and concurrent profiles - Restore 'Comparing Configurations' section deleted unintentionally in prior commit - yaml output format confirmed in source (GenerativeBenchmarkerSerialized registers json+yaml) - ghcr.io/vllm-project/guidellm container image confirmed in release.yml workflow
tylertitsworth
pushed a commit
to tylertitsworth/skills
that referenced
this pull request
Mar 4, 2026
… flag (#416) * feat(guidellm): v0.5.3 — multimodal benchmarking, mock server, rampup flag - Add version header (0.5.3), update install to guidellm[recommended] - Add container-based usage via ghcr.io/vllm-project/guidellm - Add --rampup flag: linearly ramp up request rate before steady-state - Add Multimodal Benchmarking section: audio transcription/translation and vision/image benchmarks via --request-type flag - Add Mock Server section: guidellm mock-server for CI testing without a live GPU backend; configurable latency, workers, model - Document v0.5.0 throughput mode breaking change (explicit --rate required) - Add yaml to output formats * fix(guidellm): scope --rampup to constant profile only; restore Comparing Configurations section - --rampup applies only to constant rate-type benchmarks per v0.5.3 changelog and implementing PR (vllm-project/guidellm#549); remove incorrect claim that it works with throughput and concurrent profiles - Restore 'Comparing Configurations' section deleted unintentionally in prior commit - yaml output format confirmed in source (GenerativeBenchmarkerSerialized registers json+yaml) - ghcr.io/vllm-project/guidellm container image confirmed in release.yml workflow * fix(guidellm): confirm --outputs yaml and container image source; add registry link --------- Co-authored-by: openclaw-architect[bot] <2819504+openclaw-architect[bot]@users.noreply.github.com>
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
2 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.
Summary
Simply allows a linear rampup of the constant rate profile.
Test Plan
The simplest test is to run a short constant test with 4 requests per second, with a long rampup. You can see how it ramps as expected.
There are also new tests.
Related Issues
Fulfills part of the goals of #428
Use of AI
## WRITTEN BY AI ##)