NVIDIA
NVIDIA
Merlin Inference
Container
NVIDIA
NVIDIA
Merlin Inference

This container allows users to deploy NVTabular workflows and HugeCTR or TensorFlow models to Triton Inference server for production.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
/bin/bash -c #(nop) CMD ["/bin/bash"]
05/27/2021 1:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
/bin/bash -c #(nop) ENTRYPOINT []
05/27/2021 1:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
/bin/bash -c #(nop) HEALTHCHECK &{["NONE"] "0s" "0s" "0s" '\x00'}
05/27/2021 1:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c echo $(du -h --max-depth=1 /)
05/27/2021 1:27 PM UTC
sha256:32b89641a540dd587757f2777702ec4d760a09267562daa436cd6c0ba46148b1RUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c pip install tqdm
05/27/2021 1:27 PM UTC
sha256:2367a078d284694c20bf08ca03cd1740030f1fb17bd68da4f2910bc726d31f4fRUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c rm -rf /repos
05/27/2021 1:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c echo $(du -h --max-depth=1 /)
05/27/2021 1:27 PM UTC
sha256:547f5c36e44775025cfccbd46599f00c9dec7128e3b1b7789fae9d6dd66da253RUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c ln -s /usr/local/hugectr/backends/hugectr /opt/tritonserver/backends/
05/27/2021 1:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4RUN
/bin/bash -c #(nop) ENV LD_LIBRARY_PATH=/usr/local/hugectr/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/lib:/repos/dist/lib LIBRARY_PATH=/usr/local/hugectr/lib:/usr/local/cuda/lib64/stubs: PYTHONPATH=/usr/local/hugectr/lib:
05/27/2021 1:27 PM UTC
sha256:3143189e98927e11c84ea1b1519f6a2c7b522e0c0c7fb8146afebc32d516ae4cRUN
CUDF_VER=v0.19.2 HUGECTR_VER=v3.0.1 HUGEINF_VER=0 NVTAB_VER=v0.5.3 RELEASE=true RMM_VER=v0.19.0 SM=60;61;70;75;80 TRITON_VERSION=21.03 /bin/bash -c git clone https://github.com/NVIDIA/HugeCTR.git /repos/HugeCTR &&
  cd /repos/HugeCTR &&
  if [ "$RELEASE" == "true" ] &&
  [ ${HUGECTR_VER} != 0 ]; then git fetch --all --tags &&
  git checkout tags/${HUGECTR_VER}; else git checkout master; fi &&
  git submodule update --init --recursive &&
  mkdir -p build &&
  cd build &&
  cmake -DCMAKE_BUILD_TYPE=Release -DSM=$SM -DENABLE_INFERENCE=ON .. &&
  make -j$(nproc) &&
  make install &&
  export CPATH=/usr/local/hugectr/include:$CPATH &&
  export LIBRARY_PATH=/usr/local/hugectr/lib:$LIBRARY_PATH &&
  git clone https://github.com/triton-inference-server/hugectr_backend /repos/hugectr_inference_backend &&
  cd /repos/hugectr_inference_backend &&
  if [ "$RELEASE" == "true" ] &&
  [ ${HUGEINF_VER} != 0 ] ; then git fetch --all --tags &&
  git checkout tags/${HUGEINF_VER}; else git checkout main; fi &&
  mkdir -p build &&
  cd build &&
  cmake -DCMAKE_INSTALL_PREFIX:PATH=/usr/local/hugectr .. -D TRITON_COMMON_REPO_TAG="r$TRITON_VERSION" -D TRITON_CORE_REPO_TAG="r$TRITON_VERSION" -D TRITON_BACKEND_REPO_TAG="r$TRITON_VERSION" &&
  make -j$(nproc) &&
  make install
05/27/2021 1:27 PM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.