Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver

TRITON_VERSION=2.60.0 TRITON_CONTAINER_VERSION=25.08 rm -fr /opt/hpcx/ompi

LD_LIBRARY_PATH=/usr/local/tensorrt/lib/:/opt/tritonserver/backends/tensorrtllm:/usr/local/tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64

TRITON_VERSION=2.60.0 TRITON_CONTAINER_VERSION=25.08 ldconfig &&
  ARCH="$(uname -i)" &&
  rm -fr ${TRT_ROOT}/bin ${TRT_ROOT}/targets/${ARCH}-linux-gnu/bin ${TRT_ROOT}/data &&
  rm -fr ${TRT_ROOT}/doc ${TRT_ROOT}/onnx_graphsurgeon ${TRT_ROOT}/python &&
  rm -fr ${TRT_ROOT}/samples ${TRT_ROOT}/targets/${ARCH}-linux-gnu/samples &&
  pip3 install --no-cache-dir transformers &&
  find /usr -name libtensorrt_llm.so -exec dirname {} \; > /etc/ld.so.conf.d/tensorrt-llm.conf &&
  find /opt/tritonserver -name libtritonserver.so -exec dirname {} \; > /etc/ld.so.conf.d/triton-tensorrtllm-worker.conf &&
  pip3 install --no-cache-dir grpcio-tools==1.64.0 &&
  pip3 uninstall -y setuptools

--chown=1000:1000 docker/sagemaker/serve /usr/bin/.

com.amazonaws.sagemaker.capabilities.multi-models=true

com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true

TRITON_VERSION=2.60.0 TRITON_CONTAINER_VERSION=25.08 pip3 install -r python/openai/requirements.txt

TRITON_VERSION=2.60.0 TRITON_CONTAINER_VERSION=25.08 find /opt/tritonserver/python -maxdepth 1 -type f -name "tritonserver-*.whl" | xargs -I {} pip install --upgrade {}[all] &&
  find /opt/tritonserver/python -maxdepth 1 -type f -name "tritonfrontend-*.whl" | xargs -I {} pip install --upgrade {}[all]

--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .