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`	10/12/2026 12:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	10/12/2026 12:47 AM UTC
sha256:20e38fb3196091900432c94bde9b19a2149f8c2a5c1acf5d7ebf47d816815b08	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	10/12/2026 12:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=7179c5b01b9d19acef69a6526330eb72f3b70e10`	10/12/2026 12:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	10/12/2026 12:47 AM UTC
sha256:c94b092c0fc70f93dedd2fb7a0ff9b84a2495a10cbbb06e356b0b76b793b63f8	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=55279c109fe6115979dbf3f99102b513711f99f8 TRT_LLM_VER=1.4.0rc0.dev202610120007 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	10/12/2026 12:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=55279c109fe6115979dbf3f99102b513711f99f8 TRT_LLM_VERSION=1.4.0rc0.dev202610120007`	10/12/2026 12:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	10/12/2026 12:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.4.0rc0.dev202610120007`	10/12/2026 12:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=55279c109fe6115979dbf3f99102b513711f99f8`	10/12/2026 12:43 AM UTC