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=30316da103a0904976d40901182416d29a544727`	09/03/2026 5:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRTLLM_BOLT_PROFILES=/opt/tensorrt_llm/bolt/profiles`	09/03/2026 5:30 AM UTC
sha256:0c9b4ed41a5581090efb13d33af84ff2771e34606c0cbb2e3d297cfdad19284b	COPY	`bolt_bundle/ /opt/tensorrt_llm/bolt/profiles/`	09/03/2026 5:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_PROFILES_REF=30316da103a0904976d40901182416d29a544727`	09/03/2026 5:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`BOLT_BUNDLE_DIR=bolt_bundle`	09/03/2026 5:30 AM UTC
sha256:f3fe981d2c52b69ef13ee94a98bffb9967c436c493584e3b29ffa6e2dbb8739d	RUN	`GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=5418d2205dbcf8145f6e2c873ebbff1f371f43f0 TRT_LLM_VER=1.3.0rc26.dev202609030456 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/03/2026 5:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=5418d2205dbcf8145f6e2c873ebbff1f371f43f0 TRT_LLM_VERSION=1.3.0rc26.dev202609030456`	09/03/2026 5:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/03/2026 5:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc26.dev202609030456`	09/03/2026 5:27 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=5418d2205dbcf8145f6e2c873ebbff1f371f43f0`	09/03/2026 5:27 AM UTC