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
- Enhanced flexibility for RL workflows
- Reduced preprocessing overhead
- Better integration with existing pipelines