diff --git a/.gitignore b/.gitignore
index 8444fd0..b95682d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,2 @@
 # AMD R9700 vLLM Toolbox
-amd-r9700-vllm-toolboxes/
+amd-r9700-vllm-toolboxes-main/
diff --git a/Dockerfile b/Dockerfile
index 5bcf4df..3292e25 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -6,7 +6,7 @@ RUN dnf -y install --setopt=install_weak_deps=False --nodocs \
   gcc gcc-c++ binutils make ffmpeg-free \
   cmake ninja-build aria2c tar xz vim nano \
   libdrm-devel zlib-devel openssl-devel jq \
-  numactl-devel gperftools-libs procps-ng \
+  numactl-devel gperftools-libs dialog procps-ng \
   && dnf clean all && rm -rf /var/cache/dnf/*
 
 # 2. Install "TheRock" ROCm SDK (Tarball Method)
@@ -54,24 +54,23 @@ ENV PIP_NO_CACHE_DIR=1
 RUN printf 'source /opt/venv/bin/activate\n' > /etc/profile.d/venv.sh
 RUN python -m pip install --upgrade pip wheel packaging "setuptools<80.0.0"
 
-# 5. Install PyTorch (TheRock Nightly) and PyYAML
+# 5. Install PyTorch (TheRock Nightly)
 RUN python -m pip install \
   --index-url https://rocm.nightlies.amd.com/v2-staging/gfx120X-all/ \
-  --pre torch torchaudio torchvision && \
-  python -m pip install pyyaml
+  --pre torch torchaudio torchvision
 
 # Flash-Attention
 WORKDIR /opt
 ENV FLASH_ATTENTION_TRITON_AMD_ENABLE="TRUE"
 
-RUN pip install flash-attn --no-build-isolation \
-  --index-url https://pypi.tuna.tsinghua.edu.cn/simple
+RUN git clone https://github.com/ROCm/flash-attention.git &&\ 
+  cd flash-attention &&\
+  git checkout main_perf &&\
+  python setup.py install && \
+  cd /opt && rm -rf /opt/flash-attention
 
-# 6. Clone vLLM (with retry mechanism)
-RUN for i in 1 2 3; do \
-      git clone --depth 1 https://github.com/vllm-project/vllm.git /opt/vllm && break || \
-      { echo "Attempt $i failed. Retrying in 5 seconds..."; sleep 5; rm -rf /opt/vllm 2>/dev/null; }; \
-    done
+# 6. Clone vLLM
+RUN git clone https://github.com/vllm-project/vllm.git /opt/vllm
 WORKDIR /opt/vllm
 
 # --- PATCHING ---
@@ -118,8 +117,7 @@ ENV CXX="/opt/rocm/llvm/bin/clang++"
 
 RUN export HIP_DEVICE_LIB_PATH=$(find /opt/rocm -type d -name bitcode -print -quit) && \
   echo "Compiling with Bitcode: $HIP_DEVICE_LIB_PATH" && \
-  export CMAKE_PREFIX_PATH="/opt/venv/lib64/python3.13/site-packages/torch/share/cmake:/opt/rocm" && \
-  export CMAKE_ARGS="-DROCM_PATH=/opt/rocm -DHIP_PATH=/opt/rocm -DAMDGPU_TARGETS=gfx1201 -DHIP_ARCHITECTURES=gfx1201 -DCMAKE_PREFIX_PATH=/opt/venv/lib64/python3.13/site-packages/torch/share/cmake:/opt/rocm" && \
+  export CMAKE_ARGS="-DROCM_PATH=/opt/rocm -DHIP_PATH=/opt/rocm -DAMDGPU_TARGETS=gfx1201 -DHIP_ARCHITECTURES=gfx1201" && \
   python -m pip wheel --no-build-isolation --no-deps -w /tmp/dist -v . && \
   python -m pip install /tmp/dist/*.whl