forked from phoenix-oss/llama-stack-mirror
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>
63 lines
2.3 KiB
Python
63 lines
2.3 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 logging
|
|
import warnings
|
|
from typing import Any, Dict, Set, Tuple
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.post_training import TrainingConfig
|
|
from llama_stack.providers.remote.post_training.nvidia.config import SFTLoRADefaultConfig
|
|
|
|
from .config import NvidiaPostTrainingConfig
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def warn_unsupported_params(config_dict: Any, supported_keys: Set[str], config_name: str) -> None:
|
|
keys = set(config_dict.__annotations__.keys()) if isinstance(config_dict, BaseModel) else config_dict.keys()
|
|
unsupported_params = [k for k in keys if k not in supported_keys]
|
|
if unsupported_params:
|
|
warnings.warn(
|
|
f"Parameters: {unsupported_params} in `{config_name}` not supported and will be ignored.", stacklevel=2
|
|
)
|
|
|
|
|
|
def validate_training_params(
|
|
training_config: Dict[str, Any], supported_keys: Set[str], config_name: str = "TrainingConfig"
|
|
) -> None:
|
|
"""
|
|
Validates training parameters against supported keys.
|
|
|
|
Args:
|
|
training_config: Dictionary containing training configuration parameters
|
|
supported_keys: Set of supported parameter keys
|
|
config_name: Name of the configuration for warning messages
|
|
"""
|
|
sft_lora_fields = set(SFTLoRADefaultConfig.__annotations__.keys())
|
|
training_config_fields = set(TrainingConfig.__annotations__.keys())
|
|
|
|
# Check for not supported parameters:
|
|
# - not in either of configs
|
|
# - in TrainingConfig but not in SFTLoRADefaultConfig
|
|
unsupported_params = []
|
|
for key in training_config:
|
|
if isinstance(key, str) and key not in (supported_keys.union(sft_lora_fields)):
|
|
if key in (not sft_lora_fields or training_config_fields):
|
|
unsupported_params.append(key)
|
|
|
|
if unsupported_params:
|
|
warnings.warn(
|
|
f"Parameters: {unsupported_params} in `{config_name}` are not supported and will be ignored.", stacklevel=2
|
|
)
|
|
|
|
|
|
# ToDo: implement post health checks for customizer are enabled
|
|
async def _get_health(url: str) -> Tuple[bool, bool]: ...
|
|
|
|
|
|
async def check_health(config: NvidiaPostTrainingConfig) -> None: ...
|