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=7179c5b01b9d19acef69a6526330eb72f3b70e10`	10/19/2026 12:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	10/19/2026 12:40 AM UTC
sha256:eb541ca9f409a93b60cee3e03a0dd8094cc9298fddec772b2ca50fe621a1f3fa	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	10/19/2026 12:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=7179c5b01b9d19acef69a6526330eb72f3b70e10`	10/19/2026 12:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	10/19/2026 12:40 AM UTC
sha256:32ae30b3d87859c28cb3dcd3df407c7bbbe5f463cbc4c33b0e7d53f18fe91a23	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=3163e66b2c5b8e5de2995f87dafb06ef62148446 TRT_LLM_VER=1.4.0rc1.dev202610190007 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	10/19/2026 12:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=3163e66b2c5b8e5de2995f87dafb06ef62148446 TRT_LLM_VERSION=1.4.0rc1.dev202610190007`	10/19/2026 12:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	10/19/2026 12:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.4.0rc1.dev202610190007`	10/19/2026 12:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=3163e66b2c5b8e5de2995f87dafb06ef62148446`	10/19/2026 12:36 AM UTC