Files
vllm-omni/vllm_omni/worker
tzhouam 54977bd590 Add OmniGPUModelRunner and OmniModelInputForGPU classes
- Introduced OmniGPUModelRunner for enhanced GPU model execution with state management.
- Added OmniModelInputForGPU and its builder to support additional information in model inputs.
- Implemented methods for updating request states and handling multimodal inputs.
- Enhanced input preparation for CUDA graph execution and LoRA integration.
2025-10-22 15:33:11 +08:00
..
2025-09-28 21:58:48 +08:00