diff --git a/docker/Dockerfile.ubuntu b/docker/Dockerfile.ubuntu
index 803655cb..1a255536 100644
--- a/docker/Dockerfile.ubuntu
+++ b/docker/Dockerfile.ubuntu
@@ -28,8 +28,6 @@ RUN cd /tmp && GIT_LFS_SKIP_SMUDGE=1 git clone -b  {modelscope_branch}  --single
 
 RUN cd /tmp && GIT_LFS_SKIP_SMUDGE=1 git clone -b {swift_branch}  --single-branch https://github.com/modelscope/ms-swift.git && cd ms-swift && pip install .[all] && cd / && rm -fr /tmp/ms-swift && pip cache purge;
 
-RUN cd /tmp && git clone -b ms_build --single-branch https://github.com/tastelikefeet/mmcv.git && cd mmcv && TORCH_CUDA_ARCH_LIST="6.0;6.1;7.0;7.5;8.0;8.9;9.0;8.6+PTX" MMCV_WITH_OPS=1 MAX_JOBS=32 FORCE_CUDA=1 pip install . && cd / && rm -fr /tmp/mmcv && pip cache purge;
-
 ENV SETUPTOOLS_USE_DISTUTILS=stdlib
 ENV VLLM_USE_MODELSCOPE=True
 ENV LMDEPLOY_USE_MODELSCOPE=True
diff --git a/docker/install.sh b/docker/install.sh
index 145b43ad..d1a25814 100644
--- a/docker/install.sh
+++ b/docker/install.sh
@@ -33,7 +33,7 @@ CUDA_HOME=/usr/local/cuda TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0 7.5 8.0 8.6 8.9 9.0"
 
 # pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.4cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
 # find on: https://github.com/Dao-AILab/flash-attention/releases
-cd /tmp && git clone https://github.com/Dao-AILab/flash-attention.git && cd flash-attention && python setup.py install && cd / && rm -fr /tmp/flash-attention && pip cache purge;
+cd /tmp && git clone https://github.com/Dao-AILab/flash-attention.git && cd flash-attention && pip install . && cd / && rm -fr /tmp/flash-attention && pip cache purge;
 
 pip install --no-cache-dir auto-gptq==$autogptq_version