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=6c1ce33e7fbb1730c3d85150e6ac73ebc1b76deb`	08/31/2026 8:22 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	08/31/2026 8:22 AM UTC
sha256:2a319d02f05d4338f124fba2a97ba3d30a3e9a262796ca3499e4e4621d617bc5	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	08/31/2026 8:22 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=6c1ce33e7fbb1730c3d85150e6ac73ebc1b76deb`	08/31/2026 8:22 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	08/31/2026 8:22 AM UTC
sha256:a3a8f94f44753e8e77113a9b4b54101b722e6a9e4d3e2072e3638e472b01dc2d	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=1b191b610b629c8a09bbd98516d638a6995ee89b TRT_LLM_VER=1.3.0rc26.dev202608310754 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	08/31/2026 8:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=1b191b610b629c8a09bbd98516d638a6995ee89b TRT_LLM_VERSION=1.3.0rc26.dev202608310754`	08/31/2026 8:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	08/31/2026 8:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc26.dev202608310754`	08/31/2026 8:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=1b191b610b629c8a09bbd98516d638a6995ee89b`	08/31/2026 8:19 AM UTC