forked from phoenix-oss/llama-stack-mirror
530d4bdfe1
# 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 ```
24 lines
938 B
Python
24 lines
938 B
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from pathlib import Path
|
|
|
|
from llama_stack.distribution.utils.model_utils import model_local_dir
|
|
|
|
|
|
def model_checkpoint_dir(model_id) -> str:
|
|
checkpoint_dir = Path(model_local_dir(model_id))
|
|
|
|
paths = [Path(checkpoint_dir / f"consolidated.{ext}") for ext in ["pth", "00.pth"]]
|
|
if not any(p.exists() for p in paths):
|
|
checkpoint_dir = checkpoint_dir / "original"
|
|
|
|
assert checkpoint_dir.exists(), (
|
|
f"Could not find checkpoints in: {model_local_dir(model_id)}. "
|
|
f"If you try to use the native llama model, Please download model using `llama download --model-id {model_id}`"
|
|
f"Otherwise, please save you model checkpoint under {model_local_dir(model_id)}"
|
|
)
|
|
return str(checkpoint_dir)
|