tzhouam 292da4b0d8 Merge remote-tracking branch 'origin/main' into dev/vllm-align

2026-02-23 02:09:09 +00:00

..

protocol

[Feature] Support Wan2.2 T2V and I2V Online Serving with OpenAI /v1/videos API (#1073)

2026-02-12 14:28:32 +08:00

__init__.py

[Core] Supports stage abstraction in the diffusion model (#391)

2025-12-27 01:59:33 +13:00

api_server.py

[Rebase] Rebase to vllm v0.16.0 (#1357)

2026-02-13 18:05:07 +08:00

audio_utils_mixin.py

add openai create speech endpoint (#305)

2025-12-27 13:56:51 +08:00

image_api_utils.py

DALL-E compatible image generation endpoint (#292)

2025-12-23 09:05:37 +08:00

serving_chat.py

Update vLLM wheel version in Dockerfile and enhance input processing for omni models. Added functionality to reinject omni-specific fields into processed prompts and improved handling of multimodal audio extraction in serving_chat.py. Adjusted SharedMemoryConnector logic for payload size checks and refined input preprocessing methods for better compatibility with multimodal data.

2026-02-20 08:34:53 +00:00

serving_speech.py

[Feature] : Support disaggregated inference pipeline for Qwen3_TTS (#1161)

2026-02-21 07:36:44 +08:00

serving_video.py

[Feature] Support Wan2.2 T2V and I2V Online Serving with OpenAI /v1/videos API (#1073)

2026-02-12 14:28:32 +08:00

video_api_utils.py

[Feature] Support Wan2.2 T2V and I2V Online Serving with OpenAI /v1/videos API (#1073)

2026-02-12 14:28:32 +08:00