forked from triton-inference-server/server
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile.sdk
286 lines (251 loc) · 11.1 KB
/
Dockerfile.sdk
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
# Copyright 2019-2024, NVIDIA CORPORATION & AFFILIATES. 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.
#
# Multistage build.
#
# Base image on the minimum Triton container
ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.08-py3-min
ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
ARG TRITON_PA_REPO_SUBDIR=perfanalyzerrepo
ARG TRITON_REPO_ORGANIZATION=http://github.com/triton-inference-server
ARG TRITON_COMMON_REPO_TAG=main
ARG TRITON_CORE_REPO_TAG=main
ARG TRITON_CLIENT_REPO_TAG=main
ARG TRITON_THIRD_PARTY_REPO_TAG=main
ARG TRITON_MODEL_ANALYZER_REPO_TAG=main
ARG TRITON_ENABLE_GPU=ON
ARG JAVA_BINDINGS_MAVEN_VERSION=3.8.4
ARG JAVA_BINDINGS_JAVACPP_PRESETS_TAG=1.5.8
# DCGM version to install for Model Analyzer
ARG DCGM_VERSION=3.2.6
ARG NVIDIA_TRITON_SERVER_SDK_VERSION=unknown
ARG NVIDIA_BUILD_ID=unknown
############################################################################
## Build image
############################################################################
FROM ${BASE_IMAGE} AS sdk_build
# Ensure apt-get won't prompt for selecting options
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ca-certificates \
software-properties-common \
autoconf \
automake \
build-essential \
curl \
git \
gperf \
libb64-dev \
libgoogle-perftools-dev \
libopencv-dev \
libopencv-core-dev \
libssl-dev \
libtool \
pkg-config \
python3 \
python3-pip \
python3-dev \
rapidjson-dev \
vim \
wget \
python3-pdfkit \
openjdk-11-jdk \
maven && \
pip3 install --upgrade wheel setuptools && \
pip3 install --upgrade grpcio-tools && \
pip3 install --upgrade pip
# Client build requires recent version of CMake (FetchContent required)
# Using CMAKE installation instruction from:: https://apt.kitware.com/
RUN apt update -q=2 \
&& apt install -y gpg wget \
&& wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null \
&& . /etc/os-release \
&& echo "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ $UBUNTU_CODENAME main" | tee /etc/apt/sources.list.d/kitware.list >/dev/null \
&& apt-get update -q=2 \
&& apt-get install -y --no-install-recommends cmake=3.27.7* cmake-data=3.27.7* \
&& cmake --version
# Build expects "python" executable (not python3).
RUN rm -f /usr/bin/python && \
ln -s /usr/bin/python3 /usr/bin/python
# Build the client library and examples
ARG TRITON_REPO_ORGANIZATION
ARG TRITON_CLIENT_REPO_SUBDIR
ARG TRITON_PA_REPO_SUBDIR
ARG TRITON_COMMON_REPO_TAG
ARG TRITON_CORE_REPO_TAG
ARG TRITON_CLIENT_REPO_TAG
ARG TRITON_THIRD_PARTY_REPO_TAG
ARG TRITON_ENABLE_GPU
ARG JAVA_BINDINGS_MAVEN_VERSION
ARG JAVA_BINDINGS_JAVACPP_PRESETS_TAG
ARG TARGETPLATFORM
WORKDIR /workspace
COPY TRITON_VERSION .
COPY ${TRITON_CLIENT_REPO_SUBDIR} client
COPY ${TRITON_PA_REPO_SUBDIR} perf_analyzer
WORKDIR /workspace/client_build
RUN cmake -DCMAKE_INSTALL_PREFIX=/workspace/install \
-DTRITON_VERSION=`cat /workspace/TRITON_VERSION` \
-DTRITON_REPO_ORGANIZATION=${TRITON_REPO_ORGANIZATION} \
-DTRITON_COMMON_REPO_TAG=${TRITON_COMMON_REPO_TAG} \
-DTRITON_CORE_REPO_TAG=${TRITON_CORE_REPO_TAG} \
-DTRITON_THIRD_PARTY_REPO_TAG=${TRITON_THIRD_PARTY_REPO_TAG} \
-DTRITON_ENABLE_PERF_ANALYZER=OFF \
-DTRITON_ENABLE_CC_HTTP=ON -DTRITON_ENABLE_CC_GRPC=ON \
-DTRITON_ENABLE_PYTHON_HTTP=OFF -DTRITON_ENABLE_PYTHON_GRPC=OFF \
-DTRITON_ENABLE_JAVA_HTTP=ON \
-DTRITON_ENABLE_EXAMPLES=ON -DTRITON_ENABLE_TESTS=ON \
-DTRITON_ENABLE_GPU=${TRITON_ENABLE_GPU} /workspace/client
RUN make -j16 cc-clients java-clients && \
rm -fr ~/.m2
# TODO: PA will rebuild the CC clients since it depends on it.
# This should be optimized so that we do not have to build
# the CC clients twice. Similarly, because the SDK expectation is
# that PA is packaged with the python client, we hold off on building
# the python client until now. Post-migration we should focus
# effort on de-tangling these flows.
WORKDIR /workspace/pa_build
RUN cmake -DCMAKE_INSTALL_PREFIX=/workspace/install \
-DTRITON_VERSION=`cat /workspace/TRITON_VERSION` \
-DTRITON_REPO_ORGANIZATION=${TRITON_REPO_ORGANIZATION} \
-DTRITON_COMMON_REPO_TAG=${TRITON_COMMON_REPO_TAG} \
-DTRITON_CORE_REPO_TAG=${TRITON_CORE_REPO_TAG} \
-DTRITON_CLIENT_REPO_TAG=${TRITON_CLIENT_REPO_TAG} \
-DTRITON_ENABLE_PERF_ANALYZER_C_API=ON \
-DTRITON_ENABLE_PERF_ANALYZER_TFS=ON \
-DTRITON_ENABLE_PERF_ANALYZER_TS=ON \
-DTRITON_ENABLE_PERF_ANALYZER_OPENAI=ON \
-DTRITON_ENABLE_CC_HTTP=ON \
-DTRITON_ENABLE_CC_GRPC=ON \
-DTRITON_ENABLE_PYTHON_HTTP=ON \
-DTRITON_ENABLE_PYTHON_GRPC=ON \
-DTRITON_PACKAGE_PERF_ANALYZER=ON \
-DTRITON_ENABLE_GPU=${TRITON_ENABLE_GPU} \
/workspace/perf_analyzer
RUN make -j16 perf-analyzer python-clients
RUN pip3 install build \
&& cd /workspace/perf_analyzer/genai-perf \
&& python3 -m build --wheel --outdir /workspace/install/python
# Install Java API Bindings
RUN if [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
source /workspace/client/src/java-api-bindings/scripts/install_dependencies_and_build.sh \
--maven-version ${JAVA_BINDINGS_MAVEN_VERSION} \
--core-tag ${TRITON_CORE_REPO_TAG} \
--javacpp-tag ${JAVA_BINDINGS_JAVACPP_PRESETS_TAG} \
--jar-install-path /workspace/install/java-api-bindings; \
fi
############################################################################
## Create sdk container
############################################################################
FROM ${BASE_IMAGE}
# Ensure apt-get won't prompt for selecting options
ENV DEBIAN_FRONTEND=noninteractive
ARG DCGM_VERSION
ARG TRITON_REPO_ORGANIZATION
ARG TRITON_CORE_REPO_TAG
ARG TARGETPLATFORM
ARG TRITON_ENABLE_GPU
RUN apt-get update && \
apt-get install -y --no-install-recommends \
software-properties-common \
curl \
git \
gperf \
libb64-dev \
libgoogle-perftools-dev \
libopencv-dev \
libopencv-core-dev \
libssl-dev \
libtool \
python3 \
python3-pip \
python3-dev \
vim \
wget \
python3-pdfkit \
maven \
default-jdk && \
pip3 install --upgrade wheel setuptools && \
pip3 install --upgrade grpcio-tools && \
pip3 install --upgrade pip
WORKDIR /workspace
COPY TRITON_VERSION .
COPY NVIDIA_Deep_Learning_Container_License.pdf .
COPY --from=sdk_build /workspace/client/ client/
COPY --from=sdk_build /workspace/perf_analyzer/ perf_analyzer/
COPY --from=sdk_build /workspace/install/ install/
RUN cd install && \
export VERSION=`cat /workspace/TRITON_VERSION` && \
tar zcf /workspace/v$VERSION.clients.tar.gz *
# For CI testing need to copy over L0_sdk test and L0_client_build_variants test.
RUN mkdir qa
COPY qa/L0_sdk qa/L0_sdk
COPY qa/L0_client_build_variants qa/L0_client_build_variants
# Create a directory for all the python client tests to enable unit testing
RUN mkdir -p qa/python_client_unit_tests/
COPY --from=sdk_build /workspace/client/src/python/library/tests/* qa/python_client_unit_tests/
# Install an image needed by the quickstart and other documentation.
COPY qa/images/mug.jpg images/mug.jpg
# Install the dependencies needed to run the client examples. These
# are not needed for building but including them allows this image to
# be used to run the client examples.
RUN pip3 install --upgrade "numpy<2" pillow attrdict && \
find install/python/ -maxdepth 1 -type f -name \
"tritonclient-*linux*.whl" | xargs printf -- '%s[all]' | \
xargs pip3 install --upgrade
RUN pip3 install install/python/genai_perf-*.whl
# Install DCGM
RUN if [ "$TRITON_ENABLE_GPU" = "ON" ]; then \
[ "$(uname -m)" != "x86_64" ] && arch="sbsa" || arch="x86_64" && \
curl -o /tmp/cuda-keyring.deb \
https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_all.deb \
&& apt install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
apt-get update && apt-get install -y datacenter-gpu-manager=1:${DCGM_VERSION}; \
fi
# Build expects "python" executable (not python3).
RUN rm -f /usr/bin/python && \
ln -s /usr/bin/python3 /usr/bin/python
# Install Model Analyzer
ARG TRITON_MODEL_ANALYZER_REPO_TAG
ARG TRITON_MODEL_ANALYZER_REPO="${TRITON_REPO_ORGANIZATION}/model_analyzer@${TRITON_MODEL_ANALYZER_REPO_TAG}"
RUN pip3 install "git+${TRITON_MODEL_ANALYZER_REPO}"
# Entrypoint Banner
ENV NVIDIA_PRODUCT_NAME="Triton Server SDK"
COPY docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
RUN sed 's/Server/Server SDK/' /opt/nvidia/entrypoint.d/10-banner.txt | \
sed 's/^===/=======/' > /opt/nvidia/entrypoint.d/10-banner.new && \
mv /opt/nvidia/entrypoint.d/10-banner.new /opt/nvidia/entrypoint.d/10-banner.txt
ARG NVIDIA_TRITON_SERVER_SDK_VERSION
ARG NVIDIA_BUILD_ID
ENV NVIDIA_TRITON_SERVER_SDK_VERSION=${NVIDIA_TRITON_SERVER_SDK_VERSION}
ENV NVIDIA_BUILD_ID=${NVIDIA_BUILD_ID}
ENV PATH /workspace/install/bin:${PATH}
ENV LD_LIBRARY_PATH /workspace/install/lib:${LD_LIBRARY_PATH}
# DLIS-3631: Needed to run Perf Analyzer CI tests correctly
ENV LD_LIBRARY_PATH /opt/hpcx/ompi/lib:${LD_LIBRARY_PATH}
# Set TCMALLOC_RELEASE_RATE for users setting LD_PRELOAD with tcmalloc
ENV TCMALLOC_RELEASE_RATE 200