Sy03 586cd1e8d5 [Core] Enable CUDA profiler for Omni workers ...

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

2026-09-16 11:23:36 +08:00

..

output

[Refactor] Worker/ModelRunner runner correctness fixes (G2/N) (#5452)

2026-08-20 16:47:50 +08:00

__init__.py

Initial vLLM-omni repository structure

2025-09-11 14:32:51 +08:00

base.py

[Core] Enable CUDA profiler for Omni workers

2026-09-16 11:23:36 +08:00

gpu_ar_model_runner.py

[Bugfix] Restore the async PP sampled-token broadcast in the AR runner (#7393)

2026-09-14 20:41:03 -07:00

gpu_ar_worker.py

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

gpu_generation_model_runner.py

[Bugfix] Give exact-shape codec models an unpadded input_ids view (#6775)

2026-09-04 15:28:49 -07:00

gpu_generation_worker.py

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

gpu_memory_utils.py

[Docs] Remove stale stage config references (#6270)

2026-08-20 07:09:12 +08:00

gpu_model_runner.py

[Bugfix][Qwen3-Omni] Fix synchronous Thinker pipeline parallelism (#7345)

2026-09-14 10:02:21 -07:00

memory_utils.py

[Rebase] Rebase to vllm 0.23.0 (#4286)

2026-06-13 16:43:02 +00:00

mixins.py

[Bugfix] Give exact-shape codec models an unpadded input_ids view (#6775)

2026-09-04 15:28:49 -07:00

omni_connector_model_runner_mixin.py

[Core] Split Omni connector model runner mixin (#6903)

2026-09-09 13:49:43 +08:00

omni_connector_validation.py

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

runner_assisted_metadata.py

[Perf][VoxCPM2] Add unified decode graph optimization (#4606)

2026-07-04 05:30:48 +00:00

sampling_utils.py

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

sparse_audio.py

[Refactor] Worker/ModelRunner runner correctness fixes (G2/N) (#5452)

2026-08-20 16:47:50 +08:00