phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 03:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add unsupported OpenAI mixin to all remaining inference providers

Browse source
This commit is contained in:
Ben Browning 2025-04-08 12:50:23 -04:00
parent 00c4493bda
commit 15d37fde19
7 changed files with 56 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -40,6 +40,8 @@ from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
convert_openai_chat_completion_choice,
convert_openai_chat_completion_stream,
)
@ -58,7 +60,12 @@ from .utils import _is_nvidia_hosted
logger = logging.getLogger(__name__)
class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
class NVIDIAInferenceAdapter(
Inference,
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
ModelRegistryHelper,
):
def __init__(self, config: NVIDIAConfig) -> None:
# TODO(mf): filter by available models
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)