NVIDIA
NVIDIA
TensorRT
Container
NVIDIA
NVIDIA
TensorRT

NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.

LayerLabelCreated
3f1fda88731fc8b257bf0dc81f2a1ccab846f10ba8937ff0348655d29db3076dCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
02/24/2026 12:28 AM UTC
e5ff2f89acfe505f8d4aa0125e15fc01c7676c8747f3a5b4d9cf4c0f632523ecARG
NVIDIA_BUILD_REF=6b6e6b1c6d14e05e73e3fb3b88ae49cac794aa97
02/24/2026 12:28 AM UTC
0b0a2a27744ca030f69e11d05f31b229dae5c0ddc268ac6c31d2eb122554871aLABEL
com.nvidia.build.id=272060735
02/24/2026 12:28 AM UTC
3aa676d2d5b22fd4281bca0cdd5c0656ab17fd8ff76d2daa7818ad22b411a338ENV
NVIDIA_BUILD_ID=272060735
02/24/2026 12:28 AM UTC
7020e2638fe4dec97b926f4d6da8f5b2687cc575940990cd0f6544b407f15612ARG
NVIDIA_BUILD_ID=272060735
02/24/2026 12:28 AM UTC
eda9c3313abc91f7ee542f093b00766419226c342db51d80e207b6e48f594402RUN
NVIDIA_TENSORRT_VERSION=26.02 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T= CI_JOB_TOKEN=glcbt-64_kLqXAAiKKybwKtRFsR5e ENABLE_FIPS=0 TARGETARCH=amd64 if [ "${ENABLE_FIPS}" = "1" ] &&
  [ "${TARGETARCH}" = "amd64" ]; then echo "Running fips-fix.sh"; /tmp/fips-fix.sh; fi
02/24/2026 12:28 AM UTC
a5dbc6b687f4fe600f59c3cfaa50de5013494f668df30d65870e4a519078a566ARG
TARGETARCH=amd64
02/24/2026 12:28 AM UTC
0b6513c5a9a804e9f9a09601209e3a0bd57cd355868714181f5ac20e1d45667dARG
ENABLE_FIPS=0
02/24/2026 12:28 AM UTC
0ef8f643c41a17ccbd5006138672328a6dfb11ecd0f20bb4e4ce5073e44f073dCOPY
entrypoint.d/ /opt/nvidia/entrypoint.d/
02/24/2026 12:28 AM UTC
bb11d857ae7a697885e145b543bdcc45807e33bb45cdff23176ca172268b870bRUN
NVIDIA_TENSORRT_VERSION=26.02 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T= CI_JOB_TOKEN=glcbt-64_kLqXAAiKKybwKtRFsR5e ln -sf ${_CUDA_COMPAT_PATH}/lib.real ${_CUDA_COMPAT_PATH}/lib &&
  echo ${_CUDA_COMPAT_PATH}/lib > /etc/ld.so.conf.d/00-cuda-compat.conf &&
  ldconfig &&
  rm -f ${_CUDA_COMPAT_PATH}/lib
02/24/2026 12:28 AM 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.