phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 08:59:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

impls imports remove

Browse source
This commit is contained in:
Xi Yan 2024-12-26 18:01:45 -08:00
parent c1ef055f39
commit b641902bfa
13 changed files with 97 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -5,7 +5,7 @@
# the root directory of this source tree.
import logging
from typing import AsyncGenerator
from typing import AsyncGenerator, List, Optional, Union
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
@ -13,7 +13,25 @@ from llama_models.sku_list import all_registered_models
from openai import OpenAI
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
ResponseFormatType,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (