Update llama-cpp-python installation to use --upgrade flag

- Add --upgrade flag to pip install for llama-cpp-python in build.sh
  This ensures the latest version is installed, supporting newer models
  like Qwen3.5 that may not be supported in older versions
- Add note in README about updating llama-cpp-python for newer models
- Make coderai script executable

README.md

@@ -403,6 +403,7 @@ python coderai --vulkan-list-devices
 - Q5_K_M or Q6_K for higher quality
 - Works on AMD RX 400 series and newer
 - Also works on NVIDIA GPUs but CUDA backend is preferred for NVIDIA
+- **Update llama-cpp-python** for newer model support: `pip install --upgrade llama-cpp-python --no-cache-dir`
 
 ### CPU-Only
 

build.sh

@@ -118,13 +118,13 @@ elif [ "$BACKEND" = "vulkan" ]; then
         echo -e "${GREEN}✓ Found Vulkan shader compiler: $GLSLC_CMD${NC}"
     fi
     
-    # Install llama-cpp-python with Vulkan support
+    # Install/Upgrade llama-cpp-python with Vulkan support
     # CMAKE_ARGS is used to enable Vulkan during compilation
     echo -e "${YELLOW}Building llama-cpp-python with Vulkan support (this may take several minutes)...${NC}"
     echo -e "${YELLOW}If this fails with 'Could NOT find Vulkan (missing: glslc)', install:${NC}"
     echo -e "${YELLOW}  sudo apt install glslc glslang-tools glslang-dev${NC}"
     echo ""
-    CMAKE_ARGS="-DGGML_VULKAN=ON" pip install llama-cpp-python --no-cache-dir || {
+    CMAKE_ARGS="-DGGML_VULKAN=ON" pip install --upgrade llama-cpp-python --no-cache-dir || {
         echo ""
         echo -e "${RED}Build failed!${NC}"
         echo -e "${YELLOW}If the error mentions 'missing: glslc', install the shader compiler:${NC}"