mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
[BUGFIX] clear request (#4286)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* fix * fix * fix * [Feature] support clear data * update * fix * fix * fix * fix * [BugFix] fix clear data * Update api_server.py * Update api_server.py --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
@@ -497,6 +497,7 @@ def control_scheduler(request: ControlSchedulerRequest):
|
|||||||
return JSONResponse(content=content.model_dump(), status_code=500)
|
return JSONResponse(content=content.model_dump(), status_code=500)
|
||||||
|
|
||||||
if request.reset:
|
if request.reset:
|
||||||
|
llm_engine.engine.clear_data()
|
||||||
llm_engine.engine.scheduler.reset()
|
llm_engine.engine.scheduler.reset()
|
||||||
|
|
||||||
if request.load_shards_num or request.reallocate_shard:
|
if request.load_shards_num or request.reallocate_shard:
|
||||||
|
@@ -257,6 +257,7 @@ class DynamicWeightManager:
|
|||||||
while model_weights_status.value[0] != 0:
|
while model_weights_status.value[0] != 0:
|
||||||
if model_weights_status.value[0] == 1:
|
if model_weights_status.value[0] == 1:
|
||||||
logger.info("infer engine stopped! start to load new checkpoint...")
|
logger.info("infer engine stopped! start to load new checkpoint...")
|
||||||
|
model_runner.clear_requests()
|
||||||
model_runner.update_parameters(pid)
|
model_runner.update_parameters(pid)
|
||||||
elif model_weights_status.value[0] == -1:
|
elif model_weights_status.value[0] == -1:
|
||||||
logger.info("infer engine stopped! start to clear checkpoint...")
|
logger.info("infer engine stopped! start to clear checkpoint...")
|
||||||
|
@@ -315,6 +315,8 @@ class PaddleDisWorkerProc:
|
|||||||
self.worker.model_runner,
|
self.worker.model_runner,
|
||||||
self.parallel_config.engine_worker_queue_port,
|
self.parallel_config.engine_worker_queue_port,
|
||||||
)
|
)
|
||||||
|
logger.info(f"current task queue data: {self.task_queue.num_tasks()}")
|
||||||
|
self.task_queue.clear_data()
|
||||||
self.model_weights_signal[0] = 0
|
self.model_weights_signal[0] = 0
|
||||||
logger.info(f"Rank: {self.local_rank} has updated or cleared parameters.")
|
logger.info(f"Rank: {self.local_rank} has updated or cleared parameters.")
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user