[test] suppport for modeling / [test] 建模支持

Open
#684 11 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
30/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
python, shell
Domain
infrastructure, testing-qa

Research direction

Start with runners/launch_b200-nb.sh and the requested benchmarks/glm5_fp8_b200.sh entry points, then inspect how the existing B200 benchmark workflows are structured. Confirm the specified HF_HUB_CACHE_MOUNT path and run the workflow through e2e-tests. Done means GLM-5 FP8 launches on Nvidia B200 using the new benchmark file and the end-to-end workflow passes.

Written by the indexing model from the issue text.

Description

@claude

GLM5 just released. https://cookbook.sglang.io/autoregressive/GLM/GLM-5

Create a new config for Nvidia B200 that runs GLM-5 FP8. The new benchmark file should be benchmarks/glm5_fp8_b200.sh, and should be launched from runners/launch_b200-nb.sh, but HF_HUB_CACHE_MOUNT="/mnt/data/hf_cache/hub/ . The model is already downloaded.

Then test the workflow using e2e-tests.

中文说明

测试建模支持功能。

Dominant language
Python
Stars
1.7k
Forks
303
Avg merge
1d 13h
Merged PRs (30d)
284

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from SemiAnalysisAI/InferenceX

All issues in SemiAnalysisAI/InferenceX

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.