[Feature] Support varied input formats for remaining VLM
#6 483 ouverte le 21 mai 2025
Métriques du dépôt
- Stars
- (28 442 stars)
- Métriques de merge PR
- (Merge moyen 2j 1h) (1 000 PRs mergées en 30 j)
Description
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
Currently SGL has supported varied format inputs for some of VLMs. We should support all remaining VLM and add tests (Parent issue: https://github.com/sgl-project/sglang/issues/5964)
-
We should follow the refactored process in #6659 (Note that it's somewhat outdated, check with the latest main)
-
QwenVL (@ysulsky https://github.com/sgl-project/sglang/pull/6136)
-
Gemma (@ysulsky https://github.com/sgl-project/sglang/pull/6136)
-
KimiVL (@lifuhuang https://github.com/sgl-project/sglang/pull/6599)
-
Phi4mm
-
internvl
-
mllama4
-
pixtral
-
deepseek_vl_v2
-
minicpm
-
janus_pro
Related resources
No response