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=735c55482ff95356454de016f8a52a31b9002c85`	09/27/2026 12:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	09/27/2026 12:33 AM UTC
sha256:1358ad8995fe8d6bc353b3e82501544106df05f623c67f4638b967ce1610a677	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	09/27/2026 12:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=735c55482ff95356454de016f8a52a31b9002c85`	09/27/2026 12:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	09/27/2026 12:33 AM UTC
sha256:f480a9337cf60252d07f5209f073fec39bba538696d4bcdbdd6352cb94f3b1fd	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=b88149e535265b52e8ddb1339e35710e10b7ecf8 TRT_LLM_VER=1.3.0rc29.dev202609270000 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/27/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=b88149e535265b52e8ddb1339e35710e10b7ecf8 TRT_LLM_VERSION=1.3.0rc29.dev202609270000`	09/27/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/27/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc29.dev202609270000`	09/27/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=b88149e535265b52e8ddb1339e35710e10b7ecf8`	09/27/2026 12:26 AM UTC