phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 05:24:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'meta-llama:main' into main

Browse source
This commit is contained in:
Zain Hasan 2024-09-29 11:56:29 -07:00 • committed by GitHub
commit c13b2f06af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
88 changed files with 4367 additions and 784 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_stack/providers/registry/inference.py
View file

@ -20,6 +20,7 @@ def available_providers() -> List[ProviderSpec]:
"fairscale",
"fbgemm-gpu==0.8.0",
"torch",
"torchvision",
"transformers",
"zmq",
],
@ -47,11 +48,29 @@ def available_providers() -> List[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_id="tgi",
pip_packages=["huggingface_hub"],
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.TGIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_id="hf::serverless",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.InferenceAPIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_id="hf::endpoint",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.InferenceEndpointImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
@ -72,7 +91,7 @@ def available_providers() -> List[ProviderSpec]:
],
module="llama_stack.providers.adapters.inference.together",
config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
header_extractor_class="llama_stack.providers.adapters.inference.together.TogetherHeaderExtractor",
provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator",
),
),
]

29
llama_stack/providers/registry/safety.py
View file

@ -6,7 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.distribution.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
def available_providers() -> List[ProviderSpec]:
@ -34,4 +40,25 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.adapters.safety.sample.SampleConfig",
),
),
remote_provider_spec(
api=Api.safety,
adapter=AdapterSpec(
adapter_id="bedrock",
pip_packages=["boto3"],
module="llama_stack.providers.adapters.safety.bedrock",
config_class="llama_stack.providers.adapters.safety.bedrock.BedrockSafetyConfig",
),
),
remote_provider_spec(
api=Api.safety,
adapter=AdapterSpec(
adapter_id="together",
pip_packages=[
"together",
],
module="llama_stack.providers.adapters.safety.together",
config_class="llama_stack.providers.adapters.safety.together.TogetherSafetyConfig",
provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator",
),
),
]