SunLei 3098aee05f [Perf] Support tensor transmission between work and engine with zero-copy to improve efficiency (#4839) ...

* feat(zmq): support tensor transmission with zero-copy for improved efficiency

* perf: zmq.send disable copy

* zmq recv data for debug

* convert logprobs tensor to cpu

2025-11-11 15:43:11 +08:00

..

__init__.py

[feat] support prefix cache clearing when /clear_load_weight is called (#4008)

2025-09-28 19:42:53 +08:00

engine_cache_queue.py

[Feature] EngineWorkerQueue anonymous port (#4597)

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

engine_worker_queue.py

[Bug Fix] fix bug for PD EP (#4823)

2025-11-10 15:33:29 +08:00

ipc_signal_const.py

[feat] support prefix cache clearing when /clear_load_weight is called (#4008)

2025-09-28 19:42:53 +08:00

ipc_signal.py

[BugFix] Fix profile run in pd-disaggregated deployment (#4584)

2025-10-31 14:42:00 +08:00

zmq_client.py

[Perf] Support tensor transmission between work and engine with zero-copy to improve efficiency (#4839)

2025-11-11 15:43:11 +08:00

zmq_server.py

[Perf] Support tensor transmission between work and engine with zero-copy to improve efficiency (#4839)

2025-11-11 15:43:11 +08:00