withDefaultDevice()

[atdrendel]

Expose SHLLM.withDefaultDevice(_:_:) to allow clients to run inference on the CPU or GPU.

[Copilot]

Pull Request Overview

Adds a public interface to allow clients to specify whether inference should run on CPU or GPU by exposing SHLLM.withDefaultDevice(_:_:) methods. This provides device selection flexibility that was previously unavailable to API consumers.

Key changes:

• Added synchronous and asynchronous versions of withDefaultDevice methods to the SHLLM enum
• Exported MLX.DeviceType enum to make device selection available to clients
• Added comprehensive test coverage for both CPU and GPU inference scenarios

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
Sources/SHLLM/SHLLM.swift	Implements the core withDefaultDevice methods and exports DeviceType enum
Tests/SHLLMTests/SHLLMTests.swift	Adds test functions to verify CPU and GPU inference functionality

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}