forked from PaddlePaddle/Serving
-
Notifications
You must be signed in to change notification settings - Fork 0
/
config.yml
96 lines (69 loc) · 3.37 KB
/
config.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时,会自动将rpc_port设置为http_port+1
rpc_port: 18090
#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时,不自动生成http_port
http_port: 9999
#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程,每个进程内构建grpcSever和DAG
##当build_dag_each_worker=False时,框架会设置主线程grpc线程池的max_workers=worker_num
worker_num: 20
#build_dag_each_worker, False,框架在进程内创建一条DAG;True,框架会每个进程内创建多个独立的DAG
build_dag_each_worker: false
dag:
#op资源类型, True, 为线程模型;False,为进程模型
is_thread_op: False
#重试次数
retry: 1
#使用性能分析, True,生成Timeline性能数据,对性能有一定影响;False为不使用
use_profile: false
tracer:
interval_s: 10
op:
det:
#并发数,is_thread_op=True时,为线程并发;否则为进程并发
concurrency: 6
#当op配置没有server_endpoints时,从local_service_conf读取本地服务配置
local_service_conf:
#client类型,包括brpc, grpc和local_predictor.local_predictor不启动Serving服务,进程内预测
client_type: local_predictor
#det模型路径
model_config: ocr_det_model
#Fetch结果列表,以client_config中fetch_var的alias_name为准
fetch_list: ["save_infer_model/scale_0.tmp_1"]
# device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
device_type: 0
#计算硬件ID,当devices为""或不写时为CPU预测;当devices为"0", "0,1,2"时为GPU预测,表示使用的GPU卡
devices: ""
#use_mkldnn
#use_mkldnn: True
#thread_num
thread_num: 2
#ir_optim
ir_optim: True
#开启tensorrt后,进行优化的子图包含的最少节点数
#min_subgraph_size: 13
rec:
#并发数,is_thread_op=True时,为线程并发;否则为进程并发
concurrency: 3
#超时时间, 单位ms
timeout: -1
#Serving交互重试次数,默认不重试
retry: 1
#当op配置没有server_endpoints时,从local_service_conf读取本地服务配置
local_service_conf:
#client类型,包括brpc, grpc和local_predictor。local_predictor不启动Serving服务,进程内预测
client_type: local_predictor
#rec模型路径
model_config: ocr_rec_model
#Fetch结果列表,以client_config中fetch_var的alias_name为准
fetch_list: ["save_infer_model/scale_0.tmp_1"]
# device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
device_type: 0
#计算硬件ID,当devices为""或不写时为CPU预测;当devices为"0", "0,1,2"时为GPU预测,表示使用的GPU卡
devices: ""
#use_mkldnn
#use_mkldnn: True
#thread_num
thread_num: 2
#ir_optim
ir_optim: True
#开启tensorrt后,进行优化的子图包含的最少节点数
#min_subgraph_size: 3