feat: Support for Nitro with llama.cpp vulkan backend on Mac

[hiro-v]

Problem

• Context: https://discord.com/channels/1107178041848909847/1222681742712897609
• User with Mac Intel and AMD Radeon wants to use Vulkan to accelerate models

Success Criteria

• Nitro build to support this

Additional context Add any other context or screenshots about the feature request here.