TensorRT LLM Release

NVIDIA

Container

NVIDIA

TensorRT LLM Release

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

Layer	Label		Created
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.trtllm.bolt-profiles-ref=b91158667191d2226006e6b20557bcba2d02d2a1`	09/25/2026 3:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	09/25/2026 3:02 AM UTC
sha256:547f019ca7c9b1f9fdb70c5f085cd2023cf4b3e7d58491059fdb3657d2a9bdc7	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	09/25/2026 3:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=b91158667191d2226006e6b20557bcba2d02d2a1`	09/25/2026 3:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	09/25/2026 3:02 AM UTC
sha256:d8597fea4ae16d9e2fea6c6a838e59151cd1013aadef7a6b972174932ae62c27	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=c76f4a856447820aa1f994b053da7580d69b657d TRT_LLM_VER=1.3.0rc29.dev202609250232 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/25/2026 2:58 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=c76f4a856447820aa1f994b053da7580d69b657d TRT_LLM_VERSION=1.3.0rc29.dev202609250232`	09/25/2026 2:58 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/25/2026 2:58 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc29.dev202609250232`	09/25/2026 2:58 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=c76f4a856447820aa1f994b053da7580d69b657d`	09/25/2026 2:58 AM UTC