[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 commenti) (5 reazioni) (0 assegnatari)Python (6216 fork)auto 404

Multi-modalcigood first issueperformance

Metriche repository

Star: (28.442 star)
Metriche merge PR: (Merge medio 2g 1h) (1000 PR mergiate in 30 g)

Descrizione

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:

Guida contributor

Direzione di ricerca: Esamina i test CI VLM esistenti in test/srt/test vision openai server x, identifica le lacune per le configurazioni TP, i test di stress, i test audio e proponi o implementa i casi di test. Fai riferimento alle PR correlate #8428 e #7519.
Tech stack: python
Dominio: devops
Tipo issue: Test
Difficoltà: 3
Tempo stimato: Oltre 1 settimana
Stato attività: Attiva
Chiarezza: Chiara
Prerequisiti: Git
Adatta ai principianti: 65