refactor: move all llama code to models/llama out of meta reference

[ashwinb]

What does this PR do?

Move around bits. This makes the copies from llama-models much easier to maintain and ensures we don't entangle meta-reference specific tidbits into llama-models code even by accident.

Also, kills the meta-reference-quantized-gpu distro and rolls quantization deps into meta-reference-gpu.

Test Plan

LLAMA_MODELS_DEBUG=1 \
  with-proxy llama stack run meta-reference-gpu \
  --env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct \
   --env INFERENCE_CHECKPOINT_DIR=<DIR> \
   --env MODEL_PARALLEL_SIZE=4 \
   --env QUANTIZATION_TYPE=fp8_mixed

Start a server with and without quantization. Point integration tests to it using:

pytest -s -v  tests/integration/inference/test_text_inference.py \
   --stack-config http://localhost:8321 --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct