tzhouam e4c47a2569 rebase: align vllm-omni with vLLM d2906cc19586 ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-09-10 00:41:53 +08:00

..

duplex

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

__init__.py

[Full Duplex] Feat: Support Full-Duplex realtime runtime & add MiniCPM-o 4.5 demo (#3907)

2026-07-23 16:45:18 +08:00

arg_utils.py

rebase: align vllm-omni with vLLM d2906cc19586

2026-09-10 00:41:53 +08:00

async_engine_utils.py

[Bugfix][Engine] Make abort idempotent during shutdown (#6327)

2026-08-28 19:51:25 -07:00

async_omni_engine.py

[Frontend] Add server-side VAD for turn-based omni models (#6618)

2026-09-08 03:17:00 -07:00

cfg_companion_tracker.py

[BugFix] Never dispatch diffusion with an incomplete CFG companion bundle (#5482)

2026-07-30 08:17:24 -07:00

membership_controller.py

text and image metric (#6150)

2026-08-26 02:54:45 +00:00

messages.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

mm_outputs.py

[Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)

2026-07-15 15:50:19 +08:00

orchestrator_monitor.py

[Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527)

2026-06-29 17:43:36 +02:00

orchestrator.py

[Model][JoyAI-VL-Interaction] Add native multi-stage pipeline (#5352)

2026-09-08 05:07:08 -07:00

output_modality.py

[Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)

2026-07-15 15:50:19 +08:00

output_processor.py

[Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)

2026-07-15 15:50:19 +08:00

rpc_result_router.py

[Full Duplex] Feat: Support Full-Duplex realtime runtime & add MiniCPM-o 4.5 demo (#3907)

2026-07-23 16:45:18 +08:00

serialization.py

[Refactor] Standardize data entry key names to {type}.{qualifier} format (#1829)

2026-04-25 18:15:38 +08:00

stage_admission.py

Parallel stage initialization (admission + SH/EX device locks) (Worker refactor 1/N) (#5224)

2026-09-05 22:22:41 +08:00

stage_client.py

[Diffusion] Implement paged AR↔DiT KV connector ("v1", reusing vllm's native mooncake) (#6310)

2026-09-06 05:41:54 +08:00

stage_engine_core_client.py

[Model][JoyAI-VL-Interaction] Add native multi-stage pipeline (#5352)

2026-09-08 05:07:08 -07:00

stage_engine_core_proc_manager.py

rebase: close the remaining vLLM 0.29 drift found by CI 3009

2026-09-10 00:41:53 +08:00

stage_engine_core_proc.py

Parallel stage initialization (admission + SH/EX device locks) (Worker refactor 1/N) (#5224)

2026-09-05 22:22:41 +08:00

stage_engine_startup.py

Parallel stage initialization (admission + SH/EX device locks) (Worker refactor 1/N) (#5224)

2026-09-05 22:22:41 +08:00

stage_init_utils.py

fix: reserve Qwen3-Omni NVFP4 backend fix (#7200)

2026-09-09 20:35:16 +08:00

stage_phase_lock.py

Parallel stage initialization (admission + SH/EX device locks) (Worker refactor 1/N) (#5224)

2026-09-05 22:22:41 +08:00

stage_pool.py

[Frontend] Add omni benchmark support for image and video endpoints (#4728)

2026-09-08 09:28:21 +08:00

stage_runtime.py

[Bugfix][Engine] Group overlapping device stages into one sequential init component (#7328)

2026-09-09 20:25:41 +08:00