zhouchong 5d9b5e4a5b [Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868) ...

* Refactor async_llm:cross-process with EngineService

* fix: async_llm output process

* fix: return prompt_token_ids and prompt_tokens in first res

* optimize common_engine start func

2025-12-09 10:53:40 +08:00

..

__init__.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

engine_cache_queue.py

[Feature] EngineWorkerQueue anonymous port (#4597)

2025-10-28 10:22:37 +08:00

engine_worker_queue.py

[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197)

2025-12-04 15:38:43 +08:00

fmq_factory.py

[Feature] [Benchmark]: add ZMQ-based FMQ implementation and benchmark tools (#5418)

2025-12-08 22:04:49 +08:00

fmq.py

[Feature] [Benchmark]: add ZMQ-based FMQ implementation and benchmark tools (#5418)

2025-12-08 22:04:49 +08:00

ipc_signal_const.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

ipc_signal.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

zmq_client.py

[BugFix][Metrics] Fix Prometheus Multiprocess Metrics Issues and Add ZMQ Communication Metrics (#5185)

2025-11-27 15:05:09 +08:00

zmq_server.py

[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868)

2025-12-09 10:53:40 +08:00