phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

remove SambaNovaInferenceAdapter's custom register_model in favor of the mixin's behavior

Browse source
This commit is contained in:
Matthew Farrellee 2025-07-31 15:41:29 -05:00
parent 6711fd4f5a
commit d6e0ee979c
1 changed files with 0 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

19
llama_stack/providers/remote/inference/sambanova/sambanova.py
View file

@ -4,9 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # the root directory of this source tree.
import requests
from llama_stack.apis.models import Model
from llama_stack.log import get_logger from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
@ -33,22 +30,6 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
json_schema_strict=False, # SambaNova doesn't support strict=True yet json_schema_strict=False, # SambaNova doesn't support strict=True yet
) )
async def register_model(self, model: Model) -> Model:
model_id = self.get_provider_model_id(model.provider_resource_id)
list_models_url = self.config.url + "/models"
if len(self.environment_available_models) == 0:
try:
response = requests.get(list_models_url)
response.raise_for_status()
except requests.exceptions.RequestException as e:
raise RuntimeError(f"Request to {list_models_url} failed") from e
self.environment_available_models = [model.get("id") for model in response.json().get("data", {})]
if model_id.split("sambanova/")[-1] not in self.environment_available_models:
logger.warning(f"Model {model_id} not available in {list_models_url}")
return model
async def initialize(self): async def initialize(self):
await super().initialize() await super().initialize()