phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 03:59:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

In progress: Add NVIDIA e2e notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-03 11:19:43 -04:00
parent 66d6c2580e
commit 861962fa80
18 changed files with 4888 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -243,7 +243,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
provider_model_id = self.get_provider_model_id(model_id)
request = await convert_chat_completion_request(
request=ChatCompletionRequest(
model=self.get_provider_model_id(model_id),
model=provider_model_id,
messages=messages,
sampling_params=sampling_params,
response_format=response_format,