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=347f5f172f37a1aea9a9548e550e689b956d6954`	09/20/2026 12:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	09/20/2026 12:27 AM UTC
sha256:d498fce630d7da6b70e238168666849b3c9df4c1f67252ab3657f0a578f0d47c	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	09/20/2026 12:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=347f5f172f37a1aea9a9548e550e689b956d6954`	09/20/2026 12:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	09/20/2026 12:27 AM UTC
sha256:869710010a94ad188089f115cb5b3fa01c854ebfce7a00a378fc1ad564d93ce4	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=9855bc8f368f146be27e946f13f02b2d0bb2aa7e TRT_LLM_VER=1.3.0rc28.dev202609200000 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/20/2026 12:24 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=9855bc8f368f146be27e946f13f02b2d0bb2aa7e TRT_LLM_VERSION=1.3.0rc28.dev202609200000`	09/20/2026 12:24 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/20/2026 12:24 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc28.dev202609200000`	09/20/2026 12:24 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=9855bc8f368f146be27e946f13f02b2d0bb2aa7e`	09/20/2026 12:24 AM UTC