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=f388b7c6a540364f356f200214497cdc34ce642e`	10/04/2026 12:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	10/04/2026 12:30 AM UTC
sha256:93ca28615c3cfd9b0e2352ad4e486edd61be7314d2c225206de79dcc05331b57	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	10/04/2026 12:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=f388b7c6a540364f356f200214497cdc34ce642e`	10/04/2026 12:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	10/04/2026 12:30 AM UTC
sha256:182206ea24cda38c86c4bb645143326e992e2b2927a3e520233ac83c3bd31b14	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=ace058d1f5f176673f221069baef971cfc891f90 TRT_LLM_VER=1.4.0rc0.dev202610040000 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	10/04/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=ace058d1f5f176673f221069baef971cfc891f90 TRT_LLM_VERSION=1.4.0rc0.dev202610040000`	10/04/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	10/04/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.4.0rc0.dev202610040000`	10/04/2026 12:26 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=ace058d1f5f176673f221069baef971cfc891f90`	10/04/2026 12:26 AM UTC