xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 10:36:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix environment variable setting in CPU Dockerfile (#21730)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang 2025-07-28 19:02:39 +08:00 committed by GitHub
parent 1b769dccf3
commit 65e8466c37
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 18 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
.buildkite/scripts/hardware_ci/run-cpu-test.sh
View File

@ -78,6 +78,12 @@ function cpu_tests() {
# VLLM_USE_V1=0 pytest -s -v \ # VLLM_USE_V1=0 pytest -s -v \
# tests/quantization/test_ipex_quant.py" # tests/quantization/test_ipex_quant.py"
# Run multi-lora tests
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/lora/test_qwen2vl.py"
# online serving # online serving
docker exec cpu-test-"$NUMA_NODE" bash -c ' docker exec cpu-test-"$NUMA_NODE" bash -c '
set -e set -e
@ -89,12 +95,6 @@ function cpu_tests() {
--model meta-llama/Llama-3.2-3B-Instruct \ --model meta-llama/Llama-3.2-3B-Instruct \
--num-prompts 20 \ --num-prompts 20 \
--endpoint /v1/completions' --endpoint /v1/completions'
# Run multi-lora tests
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/lora/test_qwen2vl.py"
} }
# All of CPU tests are expected to be finished less than 40 mins. # All of CPU tests are expected to be finished less than 40 mins.

25
docker/Dockerfile.cpu
View File

@ -19,16 +19,14 @@
# VLLM_CPU_AVX512VNNI=false (default)|true # VLLM_CPU_AVX512VNNI=false (default)|true
# #
######################### BASE IMAGE ######################### ######################### COMMON BASE IMAGE #########################
FROM ubuntu:22.04 AS base FROM ubuntu:22.04 AS base-common
WORKDIR /workspace/ WORKDIR /workspace/
ARG PYTHON_VERSION=3.12 ARG PYTHON_VERSION=3.12
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
ENV LD_PRELOAD=""
# Install minimal dependencies and uv # Install minimal dependencies and uv
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \ --mount=type=cache,target=/var/lib/apt,sharing=locked \
@ -63,17 +61,18 @@ RUN --mount=type=cache,target=/root/.cache/uv \
ARG TARGETARCH ARG TARGETARCH
ENV TARGETARCH=${TARGETARCH} ENV TARGETARCH=${TARGETARCH}
RUN if [ "$TARGETARCH" = "arm64" ]; then \ ######################### x86_64 BASE IMAGE #########################
PRELOAD_PATH="/usr/lib/aarch64-linux-gnu/libtcmalloc_minimal.so.4"; \ FROM base-common AS base-amd64
else \
PRELOAD_PATH="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so"; \
fi && \
echo "export LD_PRELOAD=$PRELOAD_PATH" >> ~/.bashrc
# Ensure that the LD_PRELOAD environment variable for export is in effect. ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so"
SHELL ["/bin/bash", "-c"]
ENV LD_PRELOAD=${LD_PRELOAD} ######################### arm64 BASE IMAGE #########################
FROM base-common AS base-arm64
ENV LD_PRELOAD="/usr/lib/aarch64-linux-gnu/libtcmalloc_minimal.so.4"
######################### BASE IMAGE #########################
FROM base-${TARGETARCH} AS base
RUN echo 'ulimit -c 0' >> ~/.bashrc RUN echo 'ulimit -c 0' >> ~/.bashrc