v1.1.1: Fix error state handling

• Fixes a bug where errors weren't being propagated through the stack correctly (manifested in #4).
• LlamaRunner.RunState.failed() is now created with an optional Error — this should be non-nil but because of the bridging with Objective-C/C++ there may be cases where this is not the case.

llama.swift → CameLLM:

• This is a maintenance update for llama.swift; all future feature development is happening at 🐪 CameLLM

v1.1.0: Async API

• Specifies iOS target for llama
• Defines minimum deployment targets for macOS (10.15) and iOS (13.0)
• Adds a new run() method to LlamaRunner which returns an AsyncThrowingSequence to process tokens using await in a loop
• Updates llamaTest to use the new async API
• Updates README to be more detailed and include info about the new async API