anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Model] Add native MAGI-2 Preview diffusion support (#5918)

Browse Source 
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-09-05 15:32:30 +08:00
1 parent 13c617a140
commit d4096e01fe
78 files changed
+9896 -459
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/entrypoints/openai/video_api_utils.py
+2 -2
View File
@@ -786,7 +786,7 @@ def _encode_video_bytes_legacy(
def _encode_video_bytes(
video: Any,
fps: int,
fps: int | float,
audio: Any | None = None,
audio_sample_rate: int | None = None,
video_codec_options: dict[str, str] | None = None,
@@ -908,7 +908,7 @@ def create_streaming_video_encoder(
def encode_video_base64(
video: Any,
fps: int,
fps: int | float,
audio: Any | None = None,
audio_sample_rate: int | None = None,
video_codec_options: dict[str, str] | None = None,