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	API Updates (#73)	2024-09-17 19:51:35 -07:00
describe.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
download.py	API Updates (#73)	2024-09-17 19:51:35 -07:00
list.py	feat: add substring search for model list (#1099)	2025-02-21 16:38:10 -08:00
model.py	fix: Incorrect import path for print_subcommand_description() (#1313)	2025-02-27 21:24:01 -05:00
prompt_format.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
remove.py	feat: model remove cmd (#1128)	2025-02-21 08:05:12 -08:00
safety_models.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
verify_download.py	style: update verify-download help text (#1134)	2025-02-18 10:15:26 -08:00