ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
TensorRT Inference Server
Container
NVIDIA
NVIDIA
TensorRT Inference Server

TensorRT Inference Server provides a data center inference solution optimized for NVIDIA GPUs. It maximizes inference utilization and performance on GPUs via an HTTP or gRPC endpoint, allowing remote clients to request inference for any model that is being managed by the server, as well as providing real-time metrics on latency and requests.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
11/14/2019 4:38 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
PATH=//workspace/install/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
11/14/2019 4:38 PM UTC
sha256:4036cbd9ace16a7c1100a67719c887e39ca8e2d592bffd243af9f0af3e866cf0RUN
python -m pip install --user --upgrade pip &&
  python -m pip install --upgrade install/python/tensorrtserver-*.whl numpy pillow
11/14/2019 4:37 PM UTC
sha256:88f687fe1c7e94053ab18bcf4dadd48208becbbc3d34049b34c0944e316359d3COPY
file:c8e3b9bf6aba2778f2250e95144b73aef129b32b070cb7eaf6148b53e4b19abe in images/mug.jpg
11/14/2019 4:37 PM UTC
sha256:29bb6757fcccd2a660785042498fb9e8f981d17f1982efb572f7ab84056881e5COPY
file:739b0ef33071ef274b805fc5b94589d10f3f0428805e32a8401e5b2d355eb58e in /tmp/test.sh
11/14/2019 4:37 PM UTC
sha256:851205932d7e29c6e14675b9ac4840047d3131f3f35e1cb55f6c0b3afae3942eRUN
cd install &&
  export VERSION=`cat /workspace/VERSION` &&
  tar zcf /workspace/v$VERSION.clients.tar.gz *
11/14/2019 4:37 PM UTC
sha256:ea176bb52ef79d1e814afc5f5aea154ca3cd4ee71447b45eb8c045064752d906RUN
cd build &&
  cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX:PATH=/workspace/install &&
  make -j16 trtis-clients
11/14/2019 4:37 PM UTC
sha256:434da61f3675248a5e1555a021b8b0543511f08c97e272ebbad55a33b23c1b48COPY
dir:e2efc546291c0421c8014e8e8cb647c82da7e2c9a33184072a8281cdee4f4c74 in src/core
11/14/2019 4:33 PM UTC
sha256:cffde4f98fa7fad8a702b550ada70bf8a767be5f4228514b32c472939417c0f3COPY
dir:46f6b7165b4ed04e6f53666356e5efcf49f8b82297e5ebc93464b52d44599290 in src/clients
11/12/2019 5:08 PM UTC
sha256:2ea6827249dec1fb661525ba3f35e6b0513adf08a227dd2e0a504c300dee5f9fCOPY
dir:094c925d44e2e557e72930c8e4f47603c46d25d0e50017516bb307f645279e46 in build
11/06/2019 6:25 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.