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=0f4c99e739ac4eb05722a695a9a0d8648f3d4e6e`	10/08/2026 7:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	10/08/2026 7:33 AM UTC
sha256:2f249755b1e87a169703407e317fd00d3a5a71f7157fcc069a091c44b6233478	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	10/08/2026 7:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=0f4c99e739ac4eb05722a695a9a0d8648f3d4e6e`	10/08/2026 7:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	10/08/2026 7:33 AM UTC
sha256:bf48bf1edab9e923150d1784ae36ddea190d20f09cf16139764eb0b0a2688652	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=f891b3d9bae1d8d1e6b3023e46f3b5dd3a2fe7b5 TRT_LLM_VER=1.4.0rc0.dev202610080650 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	10/08/2026 7:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=f891b3d9bae1d8d1e6b3023e46f3b5dd3a2fe7b5 TRT_LLM_VERSION=1.4.0rc0.dev202610080650`	10/08/2026 7:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	10/08/2026 7:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.4.0rc0.dev202610080650`	10/08/2026 7:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=f891b3d9bae1d8d1e6b3023e46f3b5dd3a2fe7b5`	10/08/2026 7:28 AM UTC