phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 06:32:16 +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/runpod/runpod.py
View file

@ -12,6 +12,8 @@ from llama_stack.apis.inference import * # noqa: F403
# from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
@ -38,7 +40,12 @@ RUNPOD_SUPPORTED_MODELS = {
}
class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
class RunpodInferenceAdapter(
ModelRegistryHelper,
Inference,
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
):
def __init__(self, config: RunpodImplConfig) -> None:
ModelRegistryHelper.__init__(self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS)
self.config = config