refactor(llm): replace candle backend with llama-cpp-2 for Metal GPU support

candle lacks Metal kernels for quantized GGUF models (rms-norm, QMatMul).
llama.cpp has mature Metal support and auto-detects GPU at build time.

- Replace candle-core/candle-nn/candle-transformers with llama-cpp-2
- CandleEmbed -> LlamaEmbed, CandleOrchestrator -> LlamaOrchestrator,
  CandleRerank -> LlamaRerank
- Remove select_device(), CandleQMatMul, EmbedLayer, BertLayer,
  EmbedModelVariant (llama.cpp handles all model loading internally)
- Remove metal/accelerate/cuda feature flags (llama.cpp handles GPU
  detection at CMake build time)
- LlamaContext is !Send so contexts are created per-call from the
  stored LlamaModel (which is Send+Sync)
- Public API unchanged: traits, MockLlm, download infra, FlexTokenizer,
  PromptFormat, heuristic_orchestrate all preserved
- 270 tests pass (net -1: removed select_device test)

Author: devwhodevs