Juan Pablo ZuluagaandJuanPZuluaga 8e12007ac1 [BugFix][Qwen3TTS] CodePredictor CudaGraph Pool (#2059) ...

Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>

2026-03-21 19:11:34 +08:00

..

bagel

[XPU] update bagel modeling to remove cuda hardcode, add xpu stage_config (#1931)

2026-03-19 16:55:16 +08:00

cosyvoice3

[Model] Fun cosy voice3-0.5-b-2512 (#498)

2026-03-04 19:54:59 -05:00

fish_speech

[Perf] Improve Fish Speech S2 Pro inference performance (#1859)

2026-03-21 01:15:02 -04:00

glm_image

[BugFix]: Fix bagel online inference bug (#1804)

2026-03-13 08:58:44 +00:00

hunyuan_image3

[bugfix] Add Interleaved 2D Rotary Embedding for HunyuanImage3 (#1784)

2026-03-12 21:33:03 +08:00

mammoth_moda2

add support for MammothModa2 model (#336)

2026-03-04 22:52:56 +08:00

mimo_audio

[BUGFIX] Add compatibility for mimo-audio with vLLM 0.17.0 (#1752)

2026-03-10 20:57:26 +00:00

qwen2_5_omni

[Debug] Merge vllm pull 35368 (#1534)

2026-02-28 10:39:25 +08:00

qwen3_omni

[Fixbug][Perf] Qwen3-omni: code predictor with re-prefill + SDPA and eliminate decode hot-path CPU round-trips (#2012)

2026-03-20 19:33:52 +08:00

qwen3_tts

[BugFix][Qwen3TTS] CodePredictor CudaGraph Pool (#2059)

2026-03-21 19:11:34 +08:00

voxtral_tts

[Model] Add Voxtral TTS model (#1803)

2026-03-19 16:02:11 -04:00

__init__.py

[Bagel]: Support multistage img2img (#1669)

2026-03-09 22:23:50 +08:00

output_templates.py

[Chore] Bump Python version and apply formatting changes for v0.12 release (#126)

2025-12-16 15:19:40 +08:00

registry.py

[Model] Add Voxtral TTS model (#1803)

2026-03-19 16:02:11 -04:00

utils.py

[Feature] add support for Qwen3-omni (#55)

2025-11-30 04:44:01 +08:00