Multi-modalfeaturegood first issuehelp wanted
Repository metrics
- Stars
- (28,442 stars)
- PR merge metrics
- (平均マージ 2d 1h) (30d で 1,000 merged PRs)
説明
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