refactor: move all llama code to models/llama out of meta reference (#1887)

# 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
```

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -18,6 +18,9 @@ providers:
       model: ${env.INFERENCE_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
@@ -27,6 +30,9 @@ providers:
       model: ${env.SAFETY_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
   vector_io:
   - provider_id: faiss
     provider_type: inline::faiss

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -18,6 +18,9 @@ providers:
       model: ${env.INFERENCE_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}