forked from phoenix-oss/llama-stack-mirror
c79b087552
# Context For test automation, the end goal is to run a single pytest command from root test directory (llama_stack/providers/tests/.) such that we execute push-blocking tests The work plan: 1) trigger pytest from llama_stack/providers/tests/. 2) use config file to determine what tests and parametrization we want to run # What does this PR do? 1) consolidates the "inference-models" / "embedding-model" / "judge-model" ... options in root conftest.py. Without this change, we will hit into error when trying to run `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/.` because of duplicated `addoptions` definitions across child conftest files. 2) Add a `config` option to specify test config in YAML. (see [`ci_test_config.yaml`](https://gist.github.com/sixianyi0721/5b37fbce4069139445c2f06f6e42f87e) for example config file) For provider_fixtures, we allow users to use either a default fixture combination or define their own {api:provider} combinations. ``` memory: .... fixtures: provider_fixtures: - default_fixture_param_id: ollama // use default fixture combination with param_id="ollama" in [providers/tests/memory/conftest.py](https://fburl.com/mtjzwsmk) - inference: sentence_transformers memory: faiss - default_fixture_param_id: chroma ``` 3) generate tests according to the config. Logic lives in two places: a) in `{api}/conftest.py::pytest_generate_tests`, we read from config to do parametrization. b) after test collection, in `pytest_collection_modifyitems`, we filter the tests to include only functions listed in config. ## Test Plan 1) `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/. --collect-only --config=ci_test_config.yaml` Using `--collect-only` tag to print the pytests listed in the config file (`ci_test_config.yaml`). output: [gist](https://gist.github.com/sixianyi0721/05145e60d4d085c17cfb304beeb1e60e) 2) sanity check on `--inference-model` option ``` pytest -v -s -k "ollama" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py ``` ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
101 lines
3.5 KiB
Python
101 lines
3.5 KiB
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.
|
|
import pytest
|
|
|
|
from llama_stack.apis.common.job_types import JobStatus
|
|
from llama_stack.apis.post_training import (
|
|
Checkpoint,
|
|
DataConfig,
|
|
LoraFinetuningConfig,
|
|
OptimizerConfig,
|
|
PostTrainingJob,
|
|
PostTrainingJobArtifactsResponse,
|
|
PostTrainingJobStatusResponse,
|
|
TrainingConfig,
|
|
)
|
|
|
|
# How to run this test:
|
|
#
|
|
# pytest llama_stack/providers/tests/post_training/test_post_training.py
|
|
# -m "torchtune_post_training_huggingface_datasetio"
|
|
# -v -s --tb=short --disable-warnings
|
|
|
|
|
|
class TestPostTraining:
|
|
@pytest.mark.asyncio
|
|
async def test_supervised_fine_tune(self, post_training_stack):
|
|
algorithm_config = LoraFinetuningConfig(
|
|
type="LoRA",
|
|
lora_attn_modules=["q_proj", "v_proj", "output_proj"],
|
|
apply_lora_to_mlp=True,
|
|
apply_lora_to_output=False,
|
|
rank=8,
|
|
alpha=16,
|
|
)
|
|
|
|
data_config = DataConfig(
|
|
dataset_id="alpaca",
|
|
batch_size=1,
|
|
shuffle=False,
|
|
)
|
|
|
|
optimizer_config = OptimizerConfig(
|
|
optimizer_type="adamw",
|
|
lr=3e-4,
|
|
lr_min=3e-5,
|
|
weight_decay=0.1,
|
|
num_warmup_steps=100,
|
|
)
|
|
|
|
training_config = TrainingConfig(
|
|
n_epochs=1,
|
|
data_config=data_config,
|
|
optimizer_config=optimizer_config,
|
|
max_steps_per_epoch=1,
|
|
gradient_accumulation_steps=1,
|
|
)
|
|
post_training_impl = post_training_stack
|
|
response = await post_training_impl.supervised_fine_tune(
|
|
job_uuid="1234",
|
|
model="Llama3.2-3B-Instruct",
|
|
algorithm_config=algorithm_config,
|
|
training_config=training_config,
|
|
hyperparam_search_config={},
|
|
logger_config={},
|
|
checkpoint_dir="null",
|
|
)
|
|
assert isinstance(response, PostTrainingJob)
|
|
assert response.job_uuid == "1234"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_training_jobs(self, post_training_stack):
|
|
post_training_impl = post_training_stack
|
|
jobs_list = await post_training_impl.get_training_jobs()
|
|
assert isinstance(jobs_list, List)
|
|
assert jobs_list[0].job_uuid == "1234"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_training_job_status(self, post_training_stack):
|
|
post_training_impl = post_training_stack
|
|
job_status = await post_training_impl.get_training_job_status("1234")
|
|
assert isinstance(job_status, PostTrainingJobStatusResponse)
|
|
assert job_status.job_uuid == "1234"
|
|
assert job_status.status == JobStatus.completed
|
|
assert isinstance(job_status.checkpoints[0], Checkpoint)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_training_job_artifacts(self, post_training_stack):
|
|
post_training_impl = post_training_stack
|
|
job_artifacts = await post_training_impl.get_training_job_artifacts("1234")
|
|
assert isinstance(job_artifacts, PostTrainingJobArtifactsResponse)
|
|
assert job_artifacts.job_uuid == "1234"
|
|
assert isinstance(job_artifacts.checkpoints[0], Checkpoint)
|
|
assert job_artifacts.checkpoints[0].identifier == "Llama3.2-3B-Instruct-sft-0"
|
|
assert job_artifacts.checkpoints[0].epoch == 0
|
|
assert (
|
|
"/.llama/checkpoints/Llama3.2-3B-Instruct-sft-0"
|
|
in job_artifacts.checkpoints[0].path
|
|
)
|