# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. # SPDX-License-Identifier: Apache-2.0 # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. ARG BASE_IMAGE="gitlab-master.nvidia.com:5005/dl/dgx/tritonserver/tensorrt-llm/amd64" ARG BASE_IMAGE_TAG="krish-fix-trtllm-build.23766174" FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS dev USER root # Install utilities RUN apt update -y && apt install -y git wget curl nvtop tmux vim # nats RUN wget https://github.com/nats-io/nats-server/releases/download/v2.10.24/nats-server-v2.10.24-amd64.deb && dpkg -i nats-server-v2.10.24-amd64.deb && rm nats-server-v2.10.24-amd64.deb # etcd ENV ETCD_VERSION="v3.5.18" RUN wget https://github.com/etcd-io/etcd/releases/download/$ETCD_VERSION/etcd-$ETCD_VERSION-linux-amd64.tar.gz -O /tmp/etcd.tar.gz && \ mkdir -p /usr/local/bin/etcd && \ tar -xvf /tmp/etcd.tar.gz -C /usr/local/bin/etcd --strip-components=1 && \ rm /tmp/etcd.tar.gz ENV PATH=/usr/local/bin/etcd/:$PATH # TODO: Try using uv to install tensorrtllm ARG TENSORRTLLM_PIP_WHEEL_PATH="" COPY ${TENSORRTLLM_PIP_WHEEL_PATH}/*.whl /tmp/ RUN find /tmp -name "*.whl" -exec pip install {} + # Install genai-perf for benchmarking # TODO: Move to tag when fix for genai-perf will be released ARG GENAI_PERF_TAG="25d0188713adc47868d6b3f22426375237a90529" RUN pip install "git+https://github.com/triton-inference-server/perf_analyzer.git@${GENAI_PERF_TAG}#subdirectory=genai-perf" # Install test dependencies RUN --mount=type=bind,source=./container/deps/requirements.test.txt,target=/tmp/requirements.txt \ pip install --requirement /tmp/requirements.txt ### MISC UTILITY SETUP ### # Finish pyright install RUN pyright --help > /dev/null 2>&1 # Enable Git operations in the /workspace directory RUN printf "[safe]\n directory=/workspace\n" > /root/.gitconfig RUN ln -sf /bin/bash /bin/sh # Rust build/dev dependencies RUN apt-get update && \ apt-get install --no-install-recommends --yes gdb protobuf-compiler cmake libssl-dev pkg-config RUN curl https://sh.rustup.rs -sSf | bash -s -- -y ENV PATH="/root/.cargo/bin:${PATH}" RUN rustup toolchain install 1.85.0-x86_64-unknown-linux-gnu # Working directory WORKDIR /workspace # Copy Python wheel configuration files COPY pyproject.toml /workspace/ COPY README.md /workspace/ COPY LICENSE /workspace/ COPY Cargo.toml /workspace/ COPY Cargo.lock /workspace/ COPY rust-toolchain.toml /workspace/ ARG CARGO_BUILD_JOBS ENV CARGO_TARGET_DIR=/workspace/target # Build Rust COPY lib/ /workspace/lib/ COPY components /workspace/components COPY launch /workspace/launch # TODO: Tanmay Add LLMAPI-based feature flag once the engine is ready. RUN cargo build --release --locked --features mistralrs,sglang,python && \ cargo doc --no-deps && \ cp target/release/dynamo-run /usr/local/bin && \ cp target/release/http /usr/local/bin && \ cp target/release/llmctl /usr/local/bin && \ cp target/release/metrics /usr/local/bin COPY deploy/dynamo/sdk /workspace/deploy/dynamo/sdk # Install uv, create virtualenv for general use, and build dynamo wheel COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/ RUN mkdir /opt/dynamo && \ uv venv /opt/dynamo/venv --python 3.12 && \ source /opt/dynamo/venv/bin/activate && \ cd /workspace/lib/bindings/python && \ uv build --wheel --out-dir /workspace/dist && \ uv pip install /workspace/dist/ai_dynamo_runtime*cp312*.whl && \ cd /workspace && \ uv build --wheel --out-dir /workspace/dist && \ uv pip install /workspace/dist/ai_dynamo*any.whl # Package the bindings RUN mkdir -p /opt/dynamo/bindings/wheels && \ mkdir /opt/dynamo/bindings/lib && \ cp dist/ai_dynamo_runtime*cp312*.whl /opt/dynamo/bindings/wheels/. && \ cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \ cp -r lib/bindings/c/include /opt/dynamo/bindings/. # Install dynamo.runtime and dynamo.llm wheels globally in container for tests that # currently run without virtual environment activated. # TODO: In future, we may use a virtualenv for everything and remove this. RUN pip install dist/ai_dynamo_runtime*cp312*.whl && \ pip install dist/ai_dynamo*any.whl # Tell TRTLLM worker to use the Dynamo LLM C API for KV Cache Routing ENV DYNAMO_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so" # FIXME: Copy more specific folders in for dev/debug after directory restructure COPY . /workspace # FIXME: May want a modification with dynamo banner on entry ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"] CMD []