mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
1a73f8305b
# What does this PR do? This PR adds support for NVIDIA's NeMo Customizer API to the Llama Stack post-training module. The integration enables users to fine-tune models using NVIDIA's cloud-based customization service through a consistent Llama Stack interface. [//]: # (If resolving an issue, uncomment and update the line below) [//]: # (Closes #[issue-number]) ## Test Plan [Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.*] Yet to be done Things pending under this PR: - [x] Integration of fine-tuned model(new checkpoint) for inference with nvidia llm distribution - [x] distribution integration of API - [x] Add test cases for customizer(In Progress) - [x] Documentation ``` LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/post_training/test_supervised_fine_tuning.py ============================================================================================================================================================================ test session starts ============================================================================================================================================================================= platform linux -- Python 3.10.0, pytest-8.3.4, pluggy-1.5.0 -- /home/ubuntu/llama-stack/.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.10.0', 'Platform': 'Linux-6.8.0-1021-gcp-x86_64-with-glibc2.35', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'nbval': '0.11.0', 'metadata': '3.1.1', 'anyio': '4.8.0', 'html': '4.1.1', 'asyncio': '0.25.3'}} rootdir: /home/ubuntu/llama-stack configfile: pyproject.toml plugins: nbval-0.11.0, metadata-3.1.1, anyio-4.8.0, html-4.1.1, asyncio-0.25.3 asyncio: mode=strict, asyncio_default_fixture_loop_scope=None collected 2 items tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_post_training_provider_registration[txt=8B] PASSED [ 50%] tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_list_training_jobs[txt=8B] PASSED [100%] ======================================================================================================================================================================== 2 passed, 1 warning in 0.10s ======================================================================================================================================================================== ``` cc: @mattf @dglogo @sumitb --------- Co-authored-by: Ubuntu <ubuntu@llama-stack-customizer-dev-inst-2tx95fyisatvlic4we8hidx5tfj.us-central1-a.c.brevdevprod.internal>
45 lines
1.1 KiB
Python
45 lines
1.1 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 asyncio
|
|
import pytest
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
mock_session = MagicMock()
|
|
mock_session.closed = False
|
|
mock_session.close = AsyncMock()
|
|
mock_session.__aenter__ = AsyncMock(return_value=mock_session)
|
|
mock_session.__aexit__ = AsyncMock()
|
|
|
|
|
|
@pytest.fixture(scope="session", autouse=True)
|
|
def patch_aiohttp_session():
|
|
with patch("aiohttp.ClientSession", return_value=mock_session):
|
|
yield
|
|
|
|
|
|
@pytest.fixture
|
|
def event_loop():
|
|
"""Create and provide a new event loop for each test."""
|
|
loop = asyncio.new_event_loop()
|
|
asyncio.set_event_loop(loop)
|
|
yield loop
|
|
loop.close()
|
|
|
|
|
|
@pytest.fixture
|
|
def run_async():
|
|
"""Fixture to run async functions in tests."""
|
|
|
|
def _run_async(coro):
|
|
loop = asyncio.new_event_loop()
|
|
asyncio.set_event_loop(loop)
|
|
try:
|
|
return loop.run_until_complete(coro)
|
|
finally:
|
|
loop.close()
|
|
|
|
return _run_async
|