forked from triton-inference-server/server
-
Notifications
You must be signed in to change notification settings - Fork 0
/
values.yaml
78 lines (73 loc) · 3.08 KB
/
values.yaml
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
# Copyright (c) 2019-2021, NVIDIA CORPORATION. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of NVIDIA CORPORATION nor the names of its
# contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
replicaCount: 1
image:
imageName: nvcr.io/nvidia/tritonserver:22.02-py3
pullPolicy: IfNotPresent
numGpus: 1
serverCommand: tritonserver
serverArgs:
# Model Repository Configuration (REQUIRED)
#
# Configure sources for model repository below. Multiple repositories
# can be specified
#
# To download models from an S3 bucket, uncomment and configure below
# To specify a non-AWS S3 endpoint, use the form
# s3://https://your-s3-endpoint:443/bucket/model_repository
#
#- --model-repository=s3://triton-inference-server-repository/model_repository
#
# Model Control Mode (Optional, default: none)
#
# To set model control mode, uncomment and configure below
# See https://github.com/triton-inference-server/server/blob/r22.02/docs/model_management.md
# for more details
#- --model-control-mode=explicit|poll|none
#
# Additional server args
#
# see https://github.com/triton-inference-server/server/blob/r22.02/README.md
# for more details
service:
# for Fleet Command, type should be NodePort
type: NodePort
# the following ports will be the external port opened for each service
httpNodePort: 30343
grpcNodePort: 30344
metricsNodePort: 30345
# AWS
#secret:
# update the following with base64 encoded parameters
# region: AWS_REGION
# id: AWS_SECRET_KEY_ID
# key: AWS_SECRET_ACCESS_KEY
# token: AWS_SESSION_TOKEN
# Prometheus-Operator ServiceMonitor support
# change enabled to 'true' to enable a ServiceMonitor if your cluster has
# Prometheus-Operator installed
serviceMonitor:
enabled: false