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=0829689c5238c1d1c9abe15c01e7a4b297971e5c`	10/22/2026 4:40 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	10/22/2026 4:40 PM UTC
sha256:0b24dc9e62fd25110283853a31a4a86a542c05952d9f29d2ab5becef9656062c	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	10/22/2026 4:40 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=0829689c5238c1d1c9abe15c01e7a4b297971e5c`	10/22/2026 4:40 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	10/22/2026 4:40 PM UTC
sha256:be0d69f4fb404c1dee0ea18d9483f2542b741ce0487051bb84cbcb864848cedd	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=57e20ee1bcf756167bf7d5afcb5bb8d836e8812b TRT_LLM_VER=1.4.0a0.dev202610221558 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	10/22/2026 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=57e20ee1bcf756167bf7d5afcb5bb8d836e8812b TRT_LLM_VERSION=1.4.0a0.dev202610221558`	10/22/2026 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	10/22/2026 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.4.0a0.dev202610221558`	10/22/2026 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=57e20ee1bcf756167bf7d5afcb5bb8d836e8812b`	10/22/2026 4:35 PM UTC