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

[fix] fix v0 pd, let worker step_shm_value create=False (#4781)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
Co-authored-by: xiegegege <46314656+xiegegege@users.noreply.github.com>
This commit is contained in:
李泳桦
2025-11-04 20:38:01 +08:00
committed by GitHub
parent 08abb0dd1c
commit 61856e55ce
1 changed files with 3 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
fastdeploy/worker/worker_process.py
View File

@@ -41,12 +41,7 @@ from fastdeploy.config import (
StructuredOutputsConfig,
)
from fastdeploy.inter_communicator import EngineWorkerQueue as TaskQueue
from fastdeploy.inter_communicator import (
ExistTaskStatus,
IPCSignal,
ModelWeightsStatus,
shared_memory_exists,
)
from fastdeploy.inter_communicator import ExistTaskStatus, IPCSignal, ModelWeightsStatus
from fastdeploy.model_executor.layers.quantization import parse_quant_config
from fastdeploy.model_executor.utils import v1_loader_support
from fastdeploy.platforms import current_platform
@@ -423,16 +418,12 @@ class PaddleDisWorkerProc:
def graph_optimize_and_warm_up_model(self) -> None:
self.worker.graph_optimize_and_warm_up_model()
# reset cache_messager prefilled_step signal
if self.scheduler_config.splitwise_role == "prefill":
if not envs.ENABLE_V1_KVCACHE_SCHEDULER and self.scheduler_config.splitwise_role == "prefill":
gpu_id = self.worker.model_runner.device_id
prefilled_step_name = f"splitwise_complete_prefilled_step_{self.local_rank}"
prefilled_step_idx_data = np.zeros(shape=[1], dtype=np.int32)
step_shm_value = IPCSignal(
name=prefilled_step_name,
array=prefilled_step_idx_data,
dtype=np.int32,
suffix=gpu_id,
create=not shared_memory_exists(prefilled_step_name),
name=prefilled_step_name, array=prefilled_step_idx_data, dtype=np.int32, suffix=gpu_id, create=False
)
step_shm_value.value[0] = -1