phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 22:29:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add version env variable

Browse source
This commit is contained in:
Rashmi Pawar 2025-04-16 14:33:41 +05:30
parent 436b3269dc
commit 1d960bacdc
8 changed files with 16 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -120,13 +120,10 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
"meta/llama-3.2-90b-vision-instruct": "https://ai.api.nvidia.com/v1/gr/meta/llama-3.2-90b-vision-instruct",
}
# add /v1 in case of hosted models
base_url = self._config.url
if _is_nvidia_hosted(self._config):
if provider_model_id in special_model_urls:
base_url = special_model_urls[provider_model_id]
else:
base_url = f"{self._config.url}/v1"
base_url = f"{self._config.url}/v1" if self._config.append_api_version else self._config.url
if _is_nvidia_hosted(self._config) and provider_model_id in special_model_urls:
base_url = special_model_urls[provider_model_id]
return _get_client_for_base_url(base_url)
async def completion(