Measure launch server / 测量服务器启动时间

Open
#501 4 comments 0 reactions 1 assignee View on GitHub

@functionstackx is already working on this.

Since Jan 21, 2026.

Assessment

This issue has not been assessed yet.

Description

experimental p2

@claude MVP for one of the deepseek mi300 GPU SKUs, start measuring the server startup time and output it as an different github artifact

for dsr1_fp8_mi300, measure in minutes how long sglang.launch_server takes and how long the wait_for_server_ready takes and output that as artifact & use github actions workflow to test 1 concurrency of dsr1_fp8_mi300

launch a benchmark run and then wait for it to finish and read the github artifact to ensure that the correctness & doesn't have nulls in the launch server measurement artifact

中文说明

测量推理服务器的启动时间。

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.