update Dockerfile

Dockerfile

-FROM node:20.16.0 as web_compile
-WORKDIR /home
-RUN <<EOF
-git clone https://github.com/kvcache-ai/ktransformers.git &&
-cd ktransformers/ktransformers/website/ &&
-npm install @vue/cli &&
-npm run build &&
-rm -rf node_modules
-EOF
-
+FROM pytorch/pytorch:2.5.1-cuda12.1-cudnn9-devel as compile_server
 
+# 设置代理
+ENV http_proxy=http://127.0.0.1:20181
+ENV https_proxy=http://127.0.0.1:20181
+ENV all_proxy=http://127.0.0.1:20181
 
-FROM pytorch/pytorch:2.5.1-cuda12.1-cudnn9-devel as compile_server
 ARG CPU_INSTRUCT=NATIVE
+
+# 设置工作目录和 CUDA 路径
 WORKDIR /workspace
-ENV CUDA_HOME /usr/local/cuda
-COPY --from=web_compile /home/ktransformers /workspace/ktransformers
-RUN <<EOF
-apt update -y &&  apt install -y  --no-install-recommends \
+ENV CUDA_HOME=/usr/local/cuda
+
+
+
+# 安装依赖
+RUN apt update -y
+RUN apt install -y --no-install-recommends \
+    libtbb-dev \
+    libssl-dev \
+    libcurl4-openssl-dev \
+    libaio1 \
+    libaio-dev \
+    libfmt-dev \
+    libgflags-dev \
+    zlib1g-dev \
+    patchelf \
     git \
     wget \
     vim \
     gcc \
     g++ \
-    cmake && 
-rm -rf /var/lib/apt/lists/* &&
-cd ktransformers &&
-git submodule init &&
-git submodule update &&
-pip install --upgrade pip &&
-pip install ninja pyproject numpy cpufeature &&
-pip install flash-attn &&
-CPU_INSTRUCT=${CPU_INSTRUCT}  KTRANSFORMERS_FORCE_BUILD=TRUE TORCH_CUDA_ARCH_LIST="8.0;8.6;8.7;8.9;9.0+PTX" pip install . --no-build-isolation --verbose &&
-pip cache purge &&
-cp /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /opt/conda/lib/
-EOF
-
-ENTRYPOINT ["tail", "-f", "/dev/null"]
\ No newline at end of file
+    cmake
+# 拷贝代码
+RUN git clone https://github.com/kvcache-ai/ktransformers.git 
+# 清理 apt 缓存
+RUN rm -rf /var/lib/apt/lists/*
+
+# 进入项目目录
+WORKDIR /workspace/ktransformers
+RUN git checkout work-concurrent
+# 初始化子模块
+RUN git submodule update --init --recursive
+
+# 升级 pip
+RUN pip install --upgrade pip
+
+# 安装构建依赖
+RUN pip install ninja pyproject numpy cpufeature aiohttp zmq openai
+
+# 安装 flash-attn（提前装可以避免后续某些编译依赖出错）
+RUN pip install flash-attn
+
+# 安装 ktransformers 本体（含编译）
+RUN CPU_INSTRUCT=${CPU_INSTRUCT} \
+    USE_BALANCE_SERVE=1 \
+    KTRANSFORMERS_FORCE_BUILD=TRUE \
+    TORCH_CUDA_ARCH_LIST="8.0;8.6;8.7;8.9;9.0+PTX" \
+    pip install . --no-build-isolation --verbose
+
+RUN pip install third_party/custom_flashinfer/
+# 清理 pip 缓存
+RUN pip cache purge
+
+# 拷贝 C++ 运行时库
+RUN cp /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /opt/conda/lib/
+
+# 保持容器运行（调试用）
+ENTRYPOINT ["tail", "-f", "/dev/null"]