[CI][ROCm] Ship RIXL with vllm/vllm-openai-rocm (#41634)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
This commit is contained in:
@@ -507,6 +507,10 @@ RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
|
||||
&& pip uninstall -y vllm \
|
||||
&& uv pip install --system *.whl
|
||||
|
||||
# Install RIXL wheel
|
||||
RUN --mount=type=bind,from=build_rixl,src=/app/install,target=/rixl_install \
|
||||
uv pip install --system /rixl_install/*.whl
|
||||
|
||||
ARG COMMON_WORKDIR
|
||||
ARG BASE_IMAGE
|
||||
ARG NIC_BACKEND
|
||||
@@ -517,6 +521,10 @@ COPY --from=export_vllm /benchmarks ${COMMON_WORKDIR}/vllm/benchmarks
|
||||
COPY --from=export_vllm /examples ${COMMON_WORKDIR}/vllm/examples
|
||||
COPY --from=export_vllm /docker ${COMMON_WORKDIR}/vllm/docker
|
||||
|
||||
# Use legacy IPC mode for HSA to avoid GPU memory pinning issues with UCX rocm_ipc
|
||||
# See: https://github.com/ROCm/rocm-libraries/issues/6266
|
||||
ENV HSA_ENABLE_IPC_MODE_LEGACY=1
|
||||
|
||||
ENV TOKENIZERS_PARALLELISM=false
|
||||
|
||||
# ENV that can improve safe tensor loading, and end-to-end time
|
||||
|
||||
Reference in New Issue
Block a user