Triton Inference Server

NVIDIA

Container

NVIDIA

Triton Inference Server

Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

NVIDIA AI Enterprise Supported

Layer	Label		Created
sha256:e94a920b36b7b45f94ad9d289d61d8d223724fbba3a5ca7d5c8aeeae02b577b5	COPY	`/usr/bin/serve /usr/bin/.`	09/24/2026 5:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true`	09/24/2026 5:19 AM UTC
sha256:bc27c13591fc42ede9511fb183b7f9db497f2124ad1c501b92cabd77a81e4723	COPY	`/opt/tritonserver/caches/local /opt/tritonserver/caches/local`	09/24/2026 5:19 AM UTC
sha256:81589975e0805a40b336c508dba0499ea8149b8a7b40720a729d60692ae6a5f3	COPY	`/opt/tritonserver/repoagents/checksum /opt/tritonserver/repoagents/checksum`	09/24/2026 5:19 AM UTC
sha256:9555728c57efa29d39af6f28d40003b779a2e22685bfa82a83e46502364c720c	COPY	`/opt/tritonserver/backends/python /opt/tritonserver/backends/python`	09/24/2026 5:19 AM UTC
sha256:e7c4b08ad63578299dff695f63994463324fb56b993065d256dd11ffb29e8b7e	COPY	`/opt/tritonserver/backends/identity /opt/tritonserver/backends/identity`	09/24/2026 5:19 AM UTC
sha256:c0ec36fa9744b4e957f803b92de9b458e615fe46b31bb3af57ce2bb5721188dd	COPY	`/opt/tritonserver/backends/pytorch /opt/tritonserver/backends/pytorch`	09/24/2026 5:19 AM UTC
sha256:653a857fe366499991f5bbada0ae076dcb1f4b7fd86ea3d5e18feb653ce660bb	COPY	`/opt/tritonserver/include include/`	09/24/2026 5:18 AM UTC
sha256:23152cbc08ebaee2121b602ee429d8f80b973d99d2a74270d9f5d39ee83c8cbd	COPY	`/opt/tritonserver/lib lib/`	09/24/2026 5:18 AM UTC
sha256:477da01dc6caf13f1b827accc0ff70ee6f1a7389a3290fe44d1d9e8563e49a97	COPY	`/opt/tritonserver/bin bin/`	09/24/2026 5:18 AM UTC