Sy03 023716ecc4 [Bugfix] Do not assume a stream decoder in MRv2 eager-MTP preprocess (#8484) ...

Signed-off-by: Sy03 <1370724210@qq.com>

2026-10-05 09:29:38 -04:00

..

__init__.py

[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

2026-10-05 14:11:01 +08:00

eager_mtp_kernels.py

[Model] Add single-stage Qwen3-TTS with in-Talker streaming codec decode (#8259)

2026-10-02 21:34:30 +10:00

eager_mtp.py

[Model] Batch Qwen3-TTS Talker prompt projection and settled-row preprocessing (#8477)

2026-10-04 05:08:24 +00:00

intermediate_buffer.py

[Core] Extend the shared multi-stage execution framework for mixed V1/MRv2 pipelines (#8184)

2026-09-29 07:40:57 -07:00

omni_model_state.py

[Bugfix] Do not assume a stream decoder in MRv2 eager-MTP preprocess (#8484)

2026-10-05 09:29:38 -04:00