phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: OpenAIMixin implements ModelsProtocolPrivate (#3662)

Browse source 
# What does this PR do?

add ModelsProtocolPrivate methods to OpenAIMixin

this will allow providers using OpenAIMixin to use a common interface


## Test Plan

ci w/ new tests
This commit is contained in:
Matthew Farrellee 2025-10-03 00:32:02 -04:00 • committed by Raghotham Murthy
parent cf422da825
commit 873a400544
8 changed files with 243 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -25,9 +25,6 @@ from llama_stack.apis.inference import (
ToolPromptFormat,
TopKSamplingStrategy,
)
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
@ -44,7 +41,6 @@ from .config import CerebrasImplConfig
class CerebrasInferenceAdapter(
OpenAIMixin,
ModelRegistryHelper,
Inference,
):
def __init__(self, config: CerebrasImplConfig) -> None:

2
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -44,7 +44,7 @@ from .config import FireworksImplConfig
logger = get_logger(name=__name__, category="inference::fireworks")
class FireworksInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, NeedsRequestProviderData):
class FireworksInferenceAdapter(OpenAIMixin, Inference, NeedsRequestProviderData):
embedding_model_metadata = {
"nomic-ai/nomic-embed-text-v1.5": {"embedding_dimension": 768, "context_length": 8192},
"accounts/fireworks/models/qwen3-embedding-8b": {"embedding_dimension": 4096, "context_length": 40960},

2
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -29,7 +29,6 @@ from llama_stack.apis.models import Model
from llama_stack.apis.models.models import ModelType
from llama_stack.log import get_logger
from llama_stack.models.llama.sku_list import all_registered_models
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
build_hf_repo_model_entry,
@ -65,7 +64,6 @@ def build_hf_repo_model_entries():
class _HfAdapter(
OpenAIMixin,
Inference,
ModelsProtocolPrivate,
):
url: str
api_key: SecretStr

2
llama_stack/providers/remote/inference/together/together.py
View file

@ -47,7 +47,7 @@ from .config import TogetherImplConfig
logger = get_logger(name=__name__, category="inference::together")
class TogetherInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, NeedsRequestProviderData):
class TogetherInferenceAdapter(OpenAIMixin, Inference, NeedsRequestProviderData):
embedding_model_metadata = {
"togethercomputer/m2-bert-80M-32k-retrieval": {"embedding_dimension": 768, "context_length": 32768},
"BAAI/bge-large-en-v1.5": {"embedding_dimension": 1024, "context_length": 512},