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=0eb7e98322eca12536000bc0bd3a92d4e8244710`	12/31/2018 6:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	12/31/2018 6:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=5239149`	12/31/2018 6:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=5239149`	12/31/2018 6:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	12/31/2018 6:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/opt/tensorrtserver/nvidia_entrypoint.sh`	12/31/2018 6:41 PM UTC
sha256:034121c0517e6c841bf7822da2f34183413c70045eec9d59b821b0686876b8a0	COPY	`file:efee072d36828f125fc5a39ae63dbaba3b9b4547bda7963a5be81c1a936b5661 in /opt/tensorrtserver`	12/31/2018 6:41 PM UTC
sha256:923a27c8f12cf8827119344fb03ebd1f3c8c006829350d1f28e3d6fcece26b19	COPY	`dir:51fe40547adc9db5bef5240cd4bcdc24bcab57705e27020334959346f7b0af44 in lib`	12/31/2018 6:41 PM UTC
sha256:9440e9590331965997f70acade670a86367345bb7782e3cab19c3a3c6fbe3cab	COPY	`file:bba166ae2bea79bc203cf20ebc71f2bd23a1c2c74d8a24ae3aa8308a43c64840 in bin/`	12/31/2018 6:41 PM UTC
sha256:b91561058e9bfa9d9ed034259d0abe004a95c64a5f539e0de8495482d81c6ffd	COPY	`file:5e666f796155692be498d908c47ae8d144319cd37ff7987c2f8d8fb640ef2cd7 in LICENSE.pytorch`	12/31/2018 6:41 PM UTC