Commit 0a393dcb authored by ptarasiewiczNV's avatar ptarasiewiczNV Committed by GitHub
Browse files

Update wheel build in Dockerfile.vllm_nixl (#295)

parent f7a60cba
......@@ -203,10 +203,15 @@ ENV PATH="/root/.cargo/bin:${PATH}"
# Working directory
WORKDIR /workspace
# Copy Python wheel configuration files
COPY pyproject.toml /workspace/
COPY README.md /workspace/
COPY LICENSE /workspace/
# Build Rust runtime
COPY lib/runtime /workspace/lib/runtime
RUN cd lib/runtime && \
cargo build --release --locked && \
cargo doc --no-deps
cargo build --release --locked && cargo doc --no-deps
# Build OpenAI HTTP Service binaries
COPY lib/llm /workspace/lib/llm
......@@ -222,19 +227,17 @@ RUN cd examples/rust && \
# Generate C bindings for kv cache routing in vLLM
COPY lib/bindings /workspace/lib/bindings
RUN cd lib/bindings/c && \
cargo build --release --locked && \
cargo doc --no-deps
cargo build --release --locked && cargo doc --no-deps
# Build triton_distributed wheel
RUN source /opt/triton/venv/bin/activate && \
cd lib/bindings/python && \
uv build && \
uv pip install /workspace/lib/bindings/python/dist/triton_distributed*cp312*.whl
uv build --wheel --out-dir /workspace/dist && \
uv pip install /workspace/dist/triton_distributed*cp312*.whl
# Package the bindings
RUN mkdir -p /opt/triton/bindings/wheels && \
mkdir /opt/triton/bindings/lib && \
cp lib/bindings/python/dist/triton_distributed*cp312*.whl /opt/triton/bindings/wheels/. && \
cp dist/triton_distributed*cp312*.whl /opt/triton/bindings/wheels/. && \
cp lib/bindings/c/target/release/libtriton_distributed_llm_capi.so /opt/triton/bindings/lib/. && \
cp -r lib/bindings/c/include /opt/triton/bindings/.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment