apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[RL] Adapt async rollout checkpoint update flow (#7042)

Browse Source 
* update checkpoint-transfer flow and control update_weights params

* test: add update_weights route validation
This commit is contained in:
jackyYang6
2026-03-30 19:19:34 +08:00
committed by GitHub
parent 8789329457
commit 05f2d95729
9 changed files with 58 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/worker/gpu_model_runner.py
+3 -3
View File
@@ -20,7 +20,7 @@ import queue
import time
from concurrent.futures import Future
from threading import Thread
from typing import Any, Dict, List, Optional, cast
from typing import Dict, List, Optional, cast
import numpy as np
import paddle
@@ -2692,8 +2692,8 @@ class GPUModelRunner(ModelRunnerBase):
self.dynamic_weight_manager._log_memory("dynamic weight manager update all memory")
def update_weights(self, version: str = None, rsync_config: Dict[str, Any] = None):
return self.dynamic_weight_manager.update_weights_by_rdma(version, rsync_config)
def update_weights(self, version: str = None, verify_checksum: bool = False):
return self.dynamic_weight_manager.update_weights_by_rdma(version, verify_checksum)
def sleep(self, tags):