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

Add nvidia model cache

Browse source
This commit is contained in:
Jiayi 2025-09-28 15:48:29 -07:00
parent cf386ad8f8
commit f85743dcca
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -108,8 +108,10 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
1. Dynamic models from https://integrate.api.nvidia.com/v1/models 1. Dynamic models from https://integrate.api.nvidia.com/v1/models
2. Static rerank models (which use different API endpoints) 2. Static rerank models (which use different API endpoints)
""" """
models = await super().list_models() or [] self._model_cache = {}
models = await super().list_models()
# Add rerank models
existing_ids = {m.identifier for m in models} existing_ids = {m.identifier for m in models}
for model_id, _ in self._rerank_model_endpoints.items(): for model_id, _ in self._rerank_model_endpoints.items():
if self.allowed_models and model_id not in self.allowed_models: if self.allowed_models and model_id not in self.allowed_models: