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
d9dedaab964d2efe0f04e3785e68d900189b5d82b1fde58a7ce7b55c577e965d	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /app/tensorrt_llm; ExposedPorts 6006/tcp, 8888/tcp`	01/25/2026 5:49 PM UTC
ffbb5148aeab2bf21f436d1f7b684bc610072c3d16bc7b43498ca9e863b99e14	COPY	`scripts/generate_container_oss_attribution.sh /tmp/generate_container_oss_attribution.sh`	01/25/2026 5:49 PM UTC
3f0a8fa98e7ddae666af9d0a85dee50c6f9c2b99b3e303a99507c819c1eda865	ENV	`TRT_LLM_GIT_COMMIT=45d7022cc33903509fd8045bbc577d77dd1d3e2f TRT_LLM_VERSION=1.3.0rc1`	01/25/2026 5:49 PM UTC
d9f1dba2e829da3f54c89871e67c2f9d24fe48bc6ddc2b6268858bd496deb0b1	ARG	`TARGETARCH=amd64`	01/25/2026 5:49 PM UTC
1a16607bb006ac3f7e26b92fc34eb736d2b1b66178a0be1cce8640a692a93830	ARG	`TRT_LLM_VER=1.3.0rc1`	01/25/2026 5:49 PM UTC
2b382f9e9e1be731caa2972c6a956c0064d71f7643c5343f01a0cefb11b3ee9b	ARG	`GIT_COMMIT=45d7022cc33903509fd8045bbc577d77dd1d3e2f`	01/25/2026 5:49 PM UTC
7ec21bfedeaf46203a2dcc0996d150da10f2299c8f45a1b78aac83200874aa49	RUN	`SRC_DIR=/src/tensorrt_llm CPP_BUILD_DIR=/src/tensorrt_llm/cpp/build /bin/bash -c chmod -R a+w examples && rm -v benchmarks/cpp/bertBenchmark.cpp benchmarks/cpp/gptManagerBenchmark.cpp benchmarks/cpp/disaggServerBenchmark.cpp benchmarks/cpp/CMakeLists.txt && rm -rf /root/.cache/pip`	01/25/2026 5:49 PM UTC
321127faec76e3391b16e133ff3437eb0ec6ce495b3c3e9e96f31b163b4d999b	COPY	`examples examples`	01/25/2026 5:49 PM UTC
e331484580f97abb97f41a180f9f2bc94de7df284a446f8943ee9747dcc5259b	COPY	`/src/tensorrt_llm/cpp/build/benchmarks/bertBenchmark /src/tensorrt_llm/cpp/build/benchmarks/gptManagerBenchmark /src/tensorrt_llm/cpp/build/benchmarks/disaggServerBenchmark benchmarks/cpp/`	01/25/2026 5:49 PM UTC
f4920fcc53a15fd3b87b52ea492062c3cd0019a6df813f6bdd7a1044be4160f7	ARG	`CPP_BUILD_DIR=/src/tensorrt_llm/cpp/build`	01/25/2026 5:48 PM UTC