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
sha256:13a02ec71cd84b692f03932d81db2f8848aca1dedd95054a1d5f54b5f4ba99d0	COPY	`/usr/bin/serve /usr/bin/.`	06/24/2026 11:54 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true`	06/24/2026 11:54 PM UTC
sha256:aa1cd552e41c909937f13b9f7d5b3c96018a32a7cdf567038f4e65135be4c864	COPY	`/opt/tritonserver/caches/local /opt/tritonserver/caches/local`	06/24/2026 11:54 PM UTC
sha256:981aaba96ea02011276ebb32d9d50832a65a387f91bbc774fbf3045ea02cc2e9	COPY	`/opt/tritonserver/repoagents/checksum /opt/tritonserver/repoagents/checksum`	06/24/2026 11:54 PM UTC
sha256:276b5ca0c5342e9b08597064ae034bfd55827e0dc0e8a88618de0df57237b89b	COPY	`/opt/tritonserver/backends/python /opt/tritonserver/backends/python`	06/24/2026 11:54 PM UTC
sha256:34175f5322997b42c7f6fcd96d1888145ce2fa1a9d43177185844c6af07692b0	COPY	`/opt/tritonserver/backends/identity /opt/tritonserver/backends/identity`	06/24/2026 11:54 PM UTC
sha256:e07b1adc488a3d8c215205754643bcdfdf3e6d48a4f0cfff5722c1b42b6d3759	COPY	`/opt/tritonserver/backends/pytorch /opt/tritonserver/backends/pytorch`	06/24/2026 11:54 PM UTC
sha256:4fe299323a5d38edc582880a2f26a5fabc46ad276c8371c39ec1cd6562723408	COPY	`/opt/tritonserver/include include/`	06/24/2026 11:54 PM UTC
sha256:c98301e259e722a9ca91b28e054c74e6258d2d173cc737a1ffaacc6df076a2ce	COPY	`/opt/tritonserver/lib lib/`	06/24/2026 11:54 PM UTC
sha256:d79b6dfdd6285bf4668e641110179b93dcc0e3f50b070e6fea99c41bca4dc402	COPY	`/opt/tritonserver/bin bin/`	06/24/2026 11:54 PM UTC