phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 09:30:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Clean up some more usage of direct OpenAI types

Browse source
This commit is contained in:
Ben Browning 2025-04-08 09:10:52 -04:00
parent 92fdf6d0c9
commit 5bc5fed6df
4 changed files with 10 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -9,11 +9,9 @@ from typing import Any, AsyncGenerator, Dict, List, Optional, Union
import httpx
from openai import AsyncOpenAI
from openai.types.chat import ChatCompletion as OpenAIChatCompletion
from openai.types.chat.chat_completion_chunk import (
ChatCompletionChunk as OpenAIChatCompletionChunk,
)
from openai.types.completion import Completion as OpenAICompletion
from llama_stack.apis.common.content_types import (
InterleavedContent,
@ -47,7 +45,7 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import OpenAIMessageParam
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
from llama_stack.apis.models import Model, ModelType
from llama_stack.models.llama.datatypes import BuiltinTool, StopReason, ToolCall
from llama_stack.models.llama.sku_list import all_registered_models