[Doc] Add a perf tune section (#5127)

### What this PR does / why we need it?
This patch purpose to 
1. add a  section on os point of perf tune doc
2. Set some default env in the image for performance

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-12-19 14:52:52 +08:00
committed by GitHub
parent a6eaf816f1
commit 5ab6d124e5
7 changed files with 121 additions and 12 deletions

View File

@@ -23,7 +23,9 @@ ARG SOC_VERSION="ascend910b1"
# Define environments
ENV DEBIAN_FRONTEND=noninteractive
ENV SOC_VERSION=$SOC_VERSION
ENV SOC_VERSION=$SOC_VERSION \
TASK_QUEUE_ENABLE=1 \
OMP_NUM_THREADS=1
WORKDIR /workspace
@@ -31,7 +33,7 @@ COPY . /vllm-workspace/vllm-ascend/
# Install Mooncake dependencies
RUN apt-get update -y && \
apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev && \
apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev libjemalloc2 && \
git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
cd /vllm-workspace/Mooncake && bash mooncake_installer.sh -y && \
@@ -66,4 +68,6 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
python3 -m pip cache purge
RUN echo "export LD_PRELOAD=/usr/lib/$(uname -m)-linux-gnu/libjemalloc.so.2:$LD_PRELOAD" >> ~/.bashrc
CMD ["/bin/bash"]