Add GLM5 NVFP4 disaggregated inference recipes for GB200/GB300#48
Merged
xinli-sw merged 1 commit intoNVIDIA:sa-submission-q2-2026from Apr 22, 2026
Merged
Conversation
Add 66 GLM5 NVFP4 disaggregated recipe configs for GB200 and GB300 on the sa-submission branch; standardize model path and container values across the recipe set for consistency.
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## sa-submission-q2-2026 #48 +/- ##
========================================================
Coverage ? 61.06%
========================================================
Files ? 48
Lines ? 4138
Branches ? 0
========================================================
Hits ? 2527
Misses ? 1611
Partials ? 0 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
xinli-sw
approved these changes
Apr 22, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add optimized disaggregated inference recipes for GLM-5 model with NVFP4 precision on GB200 and GB300 GPUs, including sa-bench GLM5 tokenizer configuration in the recipe set.
Recipes Added (66 YAML configs)
GB200 NVFP4:
GB300 NVFP4:
Config Details
dynamofrontend withtrtllmbackendsa-benchwithcustom_tokenizer: glm_moe_dsanvidia/GLM5-NVFP4across all GLM5 recipesnvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.3across all GLM5 recipesallconcfiles