phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 06:42:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: created dynamic model registration for openai and llama openai compat remote inference providers

Browse source 
fix: removed implementation of register_model() from LiteLLMOpenAIMixin, added log message to llama in query_available_models(), added llama-api-client dependency to pyproject.toml
This commit is contained in:
r3v5 2025-07-14 12:39:15 +01:00
parent f85189022c
commit fa5935bd80
No known key found for this signature in database
GPG key ID: 7758B9F272DE67D9
5 changed files with 49 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -13,7 +13,6 @@ from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.common.errors import UnsupportedModelError
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
@ -39,7 +38,6 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
@ -90,12 +88,6 @@ class LiteLLMOpenAIMixin(
async def shutdown(self):
pass
async def register_model(self, model: Model) -> Model:
model_id = self.get_provider_model_id(model.provider_resource_id)
if model_id is None:
raise UnsupportedModelError(model.provider_resource_id, self.alias_to_provider_id_map.keys())
return model
def get_litellm_model_name(self, model_id: str) -> str:
# users may be using openai/ prefix in their model names. the openai/models.py did this by default.
# model_id.startswith("openai/") is for backwards compatibility.