[Tracking] Improve Multimodal CI coverage · sgl-project/sglang#8496

2025-07-29T04:39:17.000Z

### Checklist - [ ] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed. - [ ] 2. Please use English, otherwise it will be closed. ### Motivation 1. All existing Multi-modal CI operations are executed on a single GPU, without considering the scenario of Tensor Parallelism (TP). There is a requirement to introduce test cases for TP-2/4 configurations. 2. The payload for VLM CI is relatively low. Stress tests are necessary, and simultaneously, it is crucial to investigate whether there are any memory leaks. 3. At present, the majority of the VLM CI is only to vision. It is essential to expand its scope to audio. 4. Welcome to add more. ### Related resources The test is under `test/srt/test_vision_openai_server_x` Related PRs: - https://github.com/sgl-project/sglang/pull/8428 - https://github.com/sgl-project/sglang/pull/7519

(3 Kommentare) (5 Reaktionen) (0 zugewiesene Personen)Python (6.216 Forks)auto 404

Multi-modalcigood first issueperformance

Repository-Metriken

Stars: (28.442 Stars)
PR-Merge-Metriken: (Durchschn. Merge 2T 1h) (1.000 gemergte PRs in 30 T)

Beschreibung

Checklist

1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
2. Please use English, otherwise it will be closed.

Motivation

All existing Multi-modal CI operations are executed on a single GPU, without considering the scenario of Tensor Parallelism (TP). There is a requirement to introduce test cases for TP-2/4 configurations.
The payload for VLM CI is relatively low. Stress tests are necessary, and simultaneously, it is crucial to investigate whether there are any memory leaks.
At present, the majority of the VLM CI is only to vision. It is essential to expand its scope to audio.
Welcome to add more.

Related resources

The test is under test/srt/test_vision_openai_server_x

Related PRs:

Contributor Guide

Research-Richtung: Untersuche die vorhandenen VLM CI Tests unter test/srt/test vision openai server x, identifiziere Lücken bei TP Konfigurationen, Stresstests, Audiotests und schlage Testfälle vor oder implementiere sie. Siehe verwandte PRs #8428 und #7519.
Tech Stack: python
Domain: devops
Issue Type: Test
Schwierigkeit: 3
Geschätzte Zeit: Über 1 Woche
Aktivitätsstatus: Aktiv
Klarheit: Klar
Voraussetzungen: Git
Einsteigerfreundlichkeit: 65