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 tests

Browse source
This commit is contained in:
Jiayi 2025-09-04 18:08:35 -07:00
parent bab9d7aaea
commit d7cbeb4b8c
6 changed files with 345 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -151,7 +151,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
for ranking in rankings:
rerank_data.append(RerankData(index=ranking["index"], relevance_score=ranking["logit"]))
# Apply max_num_results limit if specified
# Apply max_num_results limit
if max_num_results is not None:
rerank_data = rerank_data[:max_num_results]