phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-05 18:22:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Mark inline vllm as OpenAI unsupported inference

Browse source 
Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-09 08:36:01 -04:00
parent de01b1455b
commit 24cfa1ef1a
1 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -66,8 +66,10 @@ from llama_stack.providers.utils.inference.model_registry import (
ModelsProtocolPrivate, ModelsProtocolPrivate,
) )
from llama_stack.providers.utils.inference.openai_compat import ( from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionUnsupportedMixin,
OpenAICompatCompletionChoice, OpenAICompatCompletionChoice,
OpenAICompatCompletionResponse, OpenAICompatCompletionResponse,
OpenAICompletionUnsupportedMixin,
get_stop_reason, get_stop_reason,
process_chat_completion_stream_response, process_chat_completion_stream_response,
) )
@ -172,7 +174,12 @@ def _convert_sampling_params(
return vllm_sampling_params return vllm_sampling_params
class VLLMInferenceImpl(Inference, ModelsProtocolPrivate): class VLLMInferenceImpl(
Inference,
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
ModelsProtocolPrivate,
):
""" """
vLLM-based inference model adapter for Llama Stack with support for multiple models. vLLM-based inference model adapter for Llama Stack with support for multiple models.