sgl-project/sglang

[Feature] Support more multi-modal input for VLM

Open

#5,964 建立於 2025年5月2日

在 GitHub 查看
 (5 留言) (5 反應) (1 負責人)Python (6,216 fork)auto 404
Multi-modalfeaturegood first issuehelp wanted

倉庫指標

Star
 (28,442 star)
PR 合併指標
 (平均合併 2天 1小時) (30 天內合併 1,000 個 PR)

描述

Motivation

The current endpoint only supports image data input, limiting its flexibility for diverse VLM use cases. We need additional input formats, particularly for RL applications: (Could be split into multiple PRs)

  • Pre-computed Image Embeddings
  • Pixel Values
  • Pixel Value Range Parameters (min_pixel/max_pixel) for qwen-vl

Welcome to propose more.

Benefits

  1. Enhanced flexibility for RL workflows
  2. Reduced preprocessing overhead
  3. Better integration with existing pipelines

貢獻者指南