Repository navigation
Add Mistral Small 4 H100 baseline and optimized configs - #31
Merged
Merged
Conversation
aceforeverd
approved these changes
Oct 10, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds Mistral-Small-4-119B-2603 to the catalog with baseline and default optimized SGLang configurations for TP2 on two H100 GPUs, plus a self-contained performance report with English and Chinese views. The catalog records normalized throughput gains of 52.5% for 50k + 1.5k and 32.1% for 8k + 1k.
Uses the existing Gemma entry structure and the measured launch settings and results. Both variants retain
--tokenizer-path=/tokenizer; the site profile must mount the tokenizer used in the measurements at that path.Validation:
npm run validate:schemapassed. Local checks confirmed the launch flags and embedded report data match the saved comparison, the report renderer matches the reference, and the catalog index resolves the new model. No live serving or Helm validation was performed.