Draft: support apple metal framework to compute graph

[fann1993814]

1. Library setting

• [x] Add new metal setting in CMakeLists. (follow the CMakeLists.txt in llama.cpp)

2. Update Functions for metal support.

• [x] Set initial metal context in load model weight
• [x] Add buffer data from the context built from original graph in rwkv_graph
• [x] Add new compute_graph for metal in rwkv_eval
• [ ] Update operations for metal can use in rwkv_operators. (because many ggml_op cannot compute in metal, and I found the max function cannot be re-write from other ggml-functions for metal backend can be supported.)

---

#134