llamaR: Interface for Large Language Models via 'llama.cpp'

Provides 'R' bindings to 'llama.cpp' for running Large Language Models ('LLMs') locally with optional 'Vulkan' GPU acceleration via 'ggmlR'. Supports model loading, text generation, 'tokenization', token-to-piece conversion, 'embeddings' (single and batch), encoder-decoder inference, low-level batch management, chat templates, 'LoRA' adapters, explicit backend/device selection, multi-GPU split, and 'NUMA' optimization. Includes a high-level 'ragnar'-compatible embedding provider ('embed_llamar'). Built on top of 'ggmlR' for efficient tensor operations.