Ashwin Bharambe 530d4bdfe1 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 ```		2025-04-07 15:03:58 -07:00
..
__init__.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
embedding_mixin.py	fix: dont assume SentenceTransformer is imported	2025-02-25 16:53:01 -08:00
litellm_openai_mixin.py	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
model_registry.py	chore: more mypy checks (ollama, vllm, ...) (#1777)	2025-04-01 17:12:39 +02:00
openai_compat.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
prompt_adapter.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00