sgl-project/sglang

[Feature] Support varied input formats for remaining VLM

Open

#6,483 opened on May 21, 2025

View on GitHub
 (7 comments) (0 reactions) (3 assignees)Python (6,216 forks)auto 404
good first issuehelp wanted

Repository metrics

Stars
 (28,442 stars)
PR merge metrics
 (Avg merge 2d 1h) (1,000 merged PRs in 30d)

Description

Checklist

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)

Related resources

No response

Contributor guide

Research direction
Study existing implementations for QwenVL, Gemma, and KimiVL in the codebase (PRs #6136, #6599). Understand the refactored process outlined in #6659. Identify the specific files and modules for each remaining VLM (Phi4mm, internvl, etc.) and replicate the input format handling patterns.
Tech stack
python
Domain
backendmachine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
GitPythonexperience with Vision Language Models
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40