Appgithub-com-vllm-project-vllm-omni

Download Pinokio

Sign in Create accountJoin

Sign in Create accountJoin

vllm-omni

github.com/vllm-project/vllm-omniUpdated 6mo ago

Repository details

Updated 2026-04-02T12:32:57.000Z

Indexed 2026-04-02T13:00:33.821Z

A framework for efficient model inference with omni-modality models

Pinokio Apps Using This Repo

No Pinokio apps using this repo yet.

Community tagsNone yet.

Community

Sort by

Ask or share about vllm-omni…

Loading...

Loading project activity…

Pinokio

Check-ins (0)

Platforms (0)

No reports yet.

Arch (0)

No reports yet.

GPU (0)

No reports yet.

RAM (0)

No reports yet.

VRAM (0)

No reports yet.

Recent commits

[Test] Skip tests/e2e/online_serving/test_zimage_expansion.py due to issue #2435 (#2454)

zhumingjue1386 months ago50bb47a

[skip ci][Bugfix] clean useless log (#2450)

rein yang6 months agoca02351

Add VACE support for WAN 2.1 conditional video generation (#1885)

Binh Tang6 months ago458f402

[Perf] Optimize Wan2.2 rotary embedding (#2393)

Canlin Guo6 months agoe2892ef

[AutoRound] Add offline quantized `W4A16` model support (#1777)

Yi Liu6 months agoc1d2dcc

[CI] [skip ci] Rename & reset timout mins for nightly L4 tests. (#2251)

Alicia6 months ago900f6aa

[skip ci][Doc] Small fix of Doc (#2400)

Didan Deng6 months agoebc9a8d

[Test] Add voice or language test case for Qwen3-omni and Qwen-tts (#1844)

wangyu6 months ago9c2a576

[skip ci][Doc] Update RFC template doc (#2141)

Yuanheng Zhao6 months ago9595be5

[Feat] Add benchmarks for Qwen3-TTS Base/VoiceDesign Model (#2411)

Jason6 months agod3daafb