Canlin GuoandIsotr0py 9c2f7467a0 [Perf] Use vLLM's SharedFusedMoE in Qwen3-Omni (#560) ...

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2026-01-10 04:30:06 +00:00

..

layers

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

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

model_loader

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

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

models

[Perf] Use vLLM's SharedFusedMoE in Qwen3-Omni (#560)

2026-01-10 04:30:06 +00:00

stage_configs

[Feature] Support Qwen3 Omni talker cudagraph (#669)

2026-01-09 11:45:58 +08:00

stage_input_processors

[Feature] Support Qwen3 Omni talker cudagraph (#669)

2026-01-09 11:45:58 +08:00

__init__.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

custom_process_mixin.py

[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458)

2025-12-24 13:26:33 +00:00