apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Optim] Improve task-checking performance in engine-worker-queue (#5376)

Browse Source 
* [Optim] Optimize costtime in checking tasks in engine-worker-queue

* Update fastdeploy/engine/common_engine.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update fastdeploy/inter_communicator/engine_worker_queue.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* [Docs] Add docstring to set_exist_tasks method (#5382)

* Initial plan

* Add docstring to set_exist_tasks method

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* [Docs] Add docstring documentation to exist_tasks() method (#5381)

* Initial plan

* Add comprehensive docstring to exist_tasks() method

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* [Optimization] Conditionally initialize shared memory for single-node deployments only (#5383)

* Initial plan

* Conditionally initialize exist_tasks_intra_signal for single-node deployments

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* Use is_single_node flag for consistent deployment type checking

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* Remove redundant None checks in exist_tasks methods

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* format code

---------

Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
This commit is contained in:
Jiang-Jia-Jun
2025-12-11 10:33:32 +08:00
committed by GitHub
parent 2ec76352da
commit 4b3e41c665
3 changed files with 67 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/worker/worker_process.py
View File

@@ -441,7 +441,7 @@ class PaddleDisWorkerProc:
# The first worker detects whether there are tasks in the task queue
if tp_rank == 0:
if self.task_queue.num_tasks() > 0:
if self.task_queue.exist_tasks():
if envs.ENABLE_V1_KVCACHE_SCHEDULER or not (
self.fd_config.model_config.enable_mm and self.worker.exist_prefill()
):