phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 20:50:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into content-extension

Browse source
This commit is contained in:
Francisco Arceo 2025-08-28 12:58:13 -06:00 • committed by GitHub
commit 4c1f187c71
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
42 changed files with 2089 additions and 389 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/registry/inference.py
View file

@ -40,8 +40,9 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.inference,
provider_type="inline::sentence-transformers",
# CrossEncoder depends on torchao.quantization
pip_packages=[
"torch torchvision --index-url https://download.pytorch.org/whl/cpu",
"torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
"sentence-transformers --no-deps",
],
module="llama_stack.providers.inline.inference.sentence_transformers",

47
llama_stack/providers/registry/post_training.py
View file

@ -13,7 +13,7 @@ from llama_stack.providers.datatypes import AdapterSpec, Api, InlineProviderSpec
# 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=["torchtune==0.5.0", "torchao==0.8.0", "numpy"],
pip_packages=["numpy"],
module="llama_stack.providers.inline.post_training.torchtune",
config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
api_dependencies=[
@ -23,56 +23,39 @@ torchtune_def = dict(
description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.",
)
huggingface_def = dict(
api=Api.post_training,
pip_packages=["trl", "transformers", "peft", "datasets"],
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.",
)
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==0.8.0 --index-url https://download.pytorch.org/whl/cpu"]
+ ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu"]
),
},
),
InlineProviderSpec(
**{
**huggingface_def,
"provider_type": "inline::huggingface-cpu",
"pip_packages": (
cast(list[str], huggingface_def["pip_packages"])
+ ["torch --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==0.8.0"]
cast(list[str], torchtune_def["pip_packages"]) + ["torch torchtune>=0.5.0 torchao>=0.12.0"]
),
},
),
InlineProviderSpec(
**{
**huggingface_def,
"provider_type": "inline::huggingface-gpu",
"pip_packages": (cast(list[str], huggingface_def["pip_packages"]) + ["torch"]),
},
api=Api.post_training,
provider_type="inline::huggingface-gpu",
pip_packages=["trl", "transformers", "peft", "datasets", "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.",
),
remote_provider_spec(
api=Api.post_training,