Update Dockerfile

Dockerfile

@@ -24,18 +24,18 @@ WORKDIR $HOME/app
 # -DGGML_NATIVE=ON: Targets your specific Ice Lake instructions
 # -DGGML_AVX512 & VNNI: Uses the hardware acceleration flags found in your cpuinfo
 # -DGGML_CURL=ON: Enables the -hf downloading capability
-RUN git clone --depth 1 https://github.com/ggerganov/llama.cpp.git .
-RUN cmake -B build \
+RUN git clone --depth 1 https://github.com/ggerganov/llama.cpp.git . && \
+    cmake -B build \
     -DCMAKE_BUILD_TYPE=Release \
     -DGGML_NATIVE=ON \
     -DGGML_AVX512=ON \
     -DGGML_AVX512_VNNI=ON \
     -DGGML_OPENMP=ON \
     -DGGML_BLAS=ON \
-    -DGGML_BLAS_VENDOR=OpenBLAS \    
-    -DGGML_CURL=ON
-RUN cmake --build build --config --target llama-server Release -j 8
-RUN cp build/bin/llama-server . && \
+    -DGGML_BLAS_VENDOR=OpenBLAS \
+    -DGGML_CURL=ON && \
+    cmake --build build --config Release --target llama-server -j 8
+