unfriendly error message when local model fails

Following https://github.com/simonw/llm#installing-a-model-that-runs-on-your-own-machine

Error: Traceback (most recent call last):
  7: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<__mk_TVM1::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, __mk_TVM1, tvm::runtime::TVMRetValue)
  6: tvm::runtime::DeviceAPIManager::GetAPI(int, bool)
  5: tvm::runtime::DeviceAPIManager::GetAPI(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, bool) [clone .isra.0]
  4: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::vulkan::__mk_TVM0::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::vulkan::__mk_TVM0, tvm::runtime::TVMRetValue)
  3: tvm::runtime::vulkan::VulkanDeviceAPI::Global()
  2: tvm::runtime::vulkan::VulkanDeviceAPI::VulkanDeviceAPI()
  1: tvm::runtime::vulkan::VulkanInstance::GetPhysicalDevices() const
  0: _ZN3tvm7runtime6deta
  File "/workspace/tvm/src/runtime/vulkan/vulkan_instance.cc", line 144
InternalError: Check failed: (__e == VK_SUCCESS) is false: Vulkan Error, code=-3: VK_ERROR_INITIALIZATION_FAILED```

This in Windows 11 WSL ubuntu linux, quite likely without CUDA / Nvidia drivers set up properly. 

Nearby: https://github.com/gnsmrky/wsl-vulkan-mesa

Start with the local-model installation instructions and reproduce llm -m llama2 'difference between a llama and an alpaca' in WSL Ubuntu. Investigate how the Vulkan initialization failure is surfaced; done means the command reports a clearer, actionable error instead of the raw TVM traceback.