mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 20:14:13 +00:00
8422bd102a
Some checks failed
Unit Tests / unit-tests (3.13) (push) Failing after 3s
UI Tests / ui-tests (22) (push) Successful in 36s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 4s
Pre-commit / pre-commit (push) Successful in 1m12s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
# What does this PR do? currently `RemoteProviderSpec` has an `AdapterSpec` embedded in it. Remove `AdapterSpec`, and put its leftover fields into `RemoteProviderSpec`. Additionally, many of the fields were duplicated between `InlineProviderSpec` and `RemoteProviderSpec`. Move these to `ProviderSpec` so they are shared. Fixup the distro codegen to use `RemoteProviderSpec` directly rather than `remote_provider_spec` which took an AdapterSpec and returned a full provider spec ## Test Plan existing distro tests should pass. Signed-off-by: Charlie Doern <cdoern@redhat.com>
69 lines
2.9 KiB
Python
69 lines
2.9 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.
|
|
|
|
|
|
from typing import cast
|
|
|
|
from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec
|
|
|
|
# We provide two versions of these providers so that distributions can package the appropriate version of torch.
|
|
# The CPU version is used for distributions that don't have GPU support -- they result in smaller container images.
|
|
torchtune_def = dict(
|
|
api=Api.post_training,
|
|
pip_packages=["numpy"],
|
|
module="llama_stack.providers.inline.post_training.torchtune",
|
|
config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
|
|
api_dependencies=[
|
|
Api.datasetio,
|
|
Api.datasets,
|
|
],
|
|
description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.",
|
|
)
|
|
|
|
|
|
def available_providers() -> list[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
**{ # type: ignore
|
|
**torchtune_def,
|
|
"provider_type": "inline::torchtune-cpu",
|
|
"pip_packages": (
|
|
cast(list[str], torchtune_def["pip_packages"])
|
|
+ ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu"]
|
|
),
|
|
},
|
|
),
|
|
InlineProviderSpec(
|
|
**{ # type: ignore
|
|
**torchtune_def,
|
|
"provider_type": "inline::torchtune-gpu",
|
|
"pip_packages": (
|
|
cast(list[str], torchtune_def["pip_packages"]) + ["torch torchtune>=0.5.0 torchao>=0.12.0"]
|
|
),
|
|
},
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.post_training,
|
|
provider_type="inline::huggingface-gpu",
|
|
pip_packages=["trl", "transformers", "peft", "datasets>=4.0.0", "torch"],
|
|
module="llama_stack.providers.inline.post_training.huggingface",
|
|
config_class="llama_stack.providers.inline.post_training.huggingface.HuggingFacePostTrainingConfig",
|
|
api_dependencies=[
|
|
Api.datasetio,
|
|
Api.datasets,
|
|
],
|
|
description="HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem.",
|
|
),
|
|
RemoteProviderSpec(
|
|
api=Api.post_training,
|
|
adapter_type="nvidia",
|
|
provider_type="remote::nvidia",
|
|
pip_packages=["requests", "aiohttp"],
|
|
module="llama_stack.providers.remote.post_training.nvidia",
|
|
config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig",
|
|
description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.",
|
|
),
|
|
]
|