TensorRT Inference Server

NVIDIA

Container

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.

Layer	Label		Created
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.ref=533a56f164c5090d15b20d8c761be560070a16bc`	10/21/2018 8:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	10/21/2018 8:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=785465`	10/21/2018 8:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=785465`	10/21/2018 8:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	10/21/2018 8:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/opt/tensorrtserver/nvidia_entrypoint.sh`	10/21/2018 8:36 PM UTC
sha256:30add5e2601d2d05aaa28356d176950e52a28d326a98824751ca64cc05d8bb3c	COPY	`file:a21a526470474f5f0473877772fa87c942e5c79aca46d1786ca6fbde4c1a1b86 in /opt/tensorrtserver`	10/21/2018 8:36 PM UTC
sha256:32af19124d313024fb3c293306e4c55b48678ef58e1662a3cba8c8eef29f382b	COPY	`dir:7847f7644afd1d5da22aa5ca4705a7ba9d5c6e2fa9962093bbbf3614a780bec3 in lib`	10/21/2018 8:36 PM UTC
sha256:a2a131fd4b70ba73a985e15d59b1bc5d1e37ba413da9d03b1df1fc4fab35bf13	COPY	`dir:d0f3536bd685cfed121725e5ece693090a42770a0c6d290ca7b5933e47911821 in bin`	10/21/2018 8:35 PM UTC
sha256:f499098e68f27a80ec322e34832717c7194d96d32c9c193def2c85e9647340b3	COPY	`file:490bc61402332503b2610a0296d9a847e1acb12b8d1222c9313c13093e454b71 in .`	10/21/2018 8:35 PM UTC