-
Notifications
You must be signed in to change notification settings - Fork 205
[NV]Add GLM-5 NVFP4 GB300 disagg-mtp TRT-LLM benchmarks via Dynamo #1799
[NV]Add GLM-5 NVFP4 GB300 disagg-mtp TRT-LLM benchmarks via Dynamo #1799xinli-sw wants to merge 7 commits into
Conversation
Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook
If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you
PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow
As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.
If additional help is needed, PR authors can reach out to core maintainers over Slack.
1 similar comment
Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook
If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you
PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow
As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.
If additional help is needed, PR authors can reach out to core maintainers over Slack.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 6598e48. Configure here.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Duplicate non-monotonic conc-list 615 suggests misplaced entry
Medium Severity
In the ISL 8192 section, conc-list: [615] appears twice — once at line 2668 (with 10 prefill workers, decode tp=16) and again at line 2698 (with 11 prefill workers, decode tp=32) placed after the conc-list: [1229] entry. This breaks the otherwise strictly ascending concurrency order (5, 15, 30, 84, 180, 333, 615, 1229, 615, 2253). The second 615 likely has an incorrect concurrency value or is misplaced, potentially causing the benchmark to run two different hardware configurations at the same concurrency target unintentionally, or missing a distinct concurrency sweep point.
Additional Locations (1)
Reviewed by Cursor Bugbot for commit 6598e48. Configure here.
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27621692220
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27621692220
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27622387448
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27622387448
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27634400529
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27634400529
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27634553033
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27634553033
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
waiting on glm5 nvfp4 gb300 sgl mtp PR first
would like prefer if @SemiAnalysisAI/core quick whip up "best effort/good faith attempt" at an sgl glm5 nvfp4 mtp gb300 config rn and then merge then first in so then we can merge in trtllm?
Uh oh!
There was an error while loading. Please reload this page.
opened on behalf of @richardhuo-nv
Note
Low Risk
Benchmark and launcher configuration only; no application runtime or security-sensitive logic changes.
Overview
Adds
glm5-fp4-gb300-dynamo-trt-mtpto the NVIDIA master benchmark matrix: GLM-5 NVFP4 on GB300 with disaggregated prefill/decode, MTP spec-decoding, and Dynamo + TensorRT-LLM (tensorrtllm-runtime:1.3.0-dev.1-cuda13). Coverage is 23 MTP search points—13 at 1K/1K and 10 at 8K/1K—each wired to anCONFIG_FILErecipe on NVIDIA srt-slurmsa-submission-q2-2026.runners/launch_gb300-nv.shgains aglm5+fp4+dynamo-trtbranch that setsSERVED_MODEL_NAME,MODEL_PATH, andSRT_SLURM_MODEL_PREFIXfornvidia/GLM-5-NVFP4.perf-changelog.yamldocuments the new config key.Reviewed by Cursor Bugbot for commit 4dc40fe. Bugbot is set up for automated code reviews on this repo. Configure here.