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=f04859d04de68b255343a6eb4a7d9d0bbaf82ca8`	09/02/2026 12:31 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	09/02/2026 12:31 AM UTC
sha256:da5aff20e3f93a34e6746eae419a7bc1cf6d781d535094a0529dd2aa8ebb7e7a	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	09/02/2026 12:31 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=f04859d04de68b255343a6eb4a7d9d0bbaf82ca8`	09/02/2026 12:31 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	09/02/2026 12:31 AM UTC
sha256:06809f060025fb000ef6e403708b5a1a1c834eb4f14a9a4ee37c4c0fcf39e225	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=fcc84548ee6000530222600b33c4e733eaaf4de1 TRT_LLM_VER=1.3.0rc26.dev202609020001 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/02/2026 12:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=fcc84548ee6000530222600b33c4e733eaaf4de1 TRT_LLM_VERSION=1.3.0rc26.dev202609020001`	09/02/2026 12:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/02/2026 12:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc26.dev202609020001`	09/02/2026 12:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=fcc84548ee6000530222600b33c4e733eaaf4de1`	09/02/2026 12:28 AM UTC