mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
940968ee3f
* fixing safety inference and safety adapter for new API spec. Pinned the llama_models version to 0.0.24 as the latest version 0.0.35 has the model descriptor name changed. I was getting the missing package error during runtime as well, hence added the dependency to requirements.txt * support Llama 3.2 models in Together inference adapter and cleanup Together safety adapter * fixing model names * adding vision guard to Together safety
97 lines
3.6 KiB
Python
97 lines
3.6 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 List
|
|
|
|
from llama_stack.distribution.datatypes import * # noqa: F403
|
|
|
|
|
|
def available_providers() -> List[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_id="meta-reference",
|
|
pip_packages=[
|
|
"accelerate",
|
|
"blobfile",
|
|
"fairscale",
|
|
"fbgemm-gpu==0.8.0",
|
|
"torch",
|
|
"torchvision",
|
|
"transformers",
|
|
"zmq",
|
|
],
|
|
module="llama_stack.providers.impls.meta_reference.inference",
|
|
config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceImplConfig",
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_id="sample",
|
|
pip_packages=[],
|
|
module="llama_stack.providers.adapters.inference.sample",
|
|
config_class="llama_stack.providers.adapters.inference.sample.SampleConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_id="ollama",
|
|
pip_packages=["ollama"],
|
|
module="llama_stack.providers.adapters.inference.ollama",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_id="tgi",
|
|
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(
|
|
adapter_id="fireworks",
|
|
pip_packages=[
|
|
"fireworks-ai",
|
|
],
|
|
module="llama_stack.providers.adapters.inference.fireworks",
|
|
config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_id="together",
|
|
pip_packages=[
|
|
"together",
|
|
],
|
|
module="llama_stack.providers.adapters.inference.together",
|
|
config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
|
|
provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator",
|
|
),
|
|
),
|
|
]
|