sgl-project/sglang

[Feature] Support more multi-modal input for VLM

Open

#5964 aperta il 2 mag 2025

Vedi su GitHub
 (5 commenti) (5 reazioni) (1 assegnatario)Python (6216 fork)auto 404
Multi-modalfeaturegood first issuehelp wanted

Metriche repository

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

Descrizione

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

Guida contributor