Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -23,7 +23,7 @@ import logging
|
||||
import os
|
||||
import sys
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Callable, Optional
|
||||
from collections.abc import Callable
|
||||
|
||||
import aiohttp
|
||||
import requests
|
||||
@@ -49,12 +49,9 @@ class Proxy:
|
||||
decode_instances: list[str],
|
||||
model: str,
|
||||
scheduling_policy: SchedulingPolicy,
|
||||
custom_create_completion: Optional[
|
||||
Callable[[Request], StreamingResponse]
|
||||
] = None,
|
||||
custom_create_chat_completion: Optional[
|
||||
Callable[[Request], StreamingResponse]
|
||||
] = None,
|
||||
custom_create_completion: Callable[[Request], StreamingResponse] | None = None,
|
||||
custom_create_chat_completion: Callable[[Request], StreamingResponse]
|
||||
| None = None,
|
||||
):
|
||||
self.prefill_instances = prefill_instances
|
||||
self.decode_instances = decode_instances
|
||||
@@ -348,9 +345,9 @@ class ProxyServer:
|
||||
def __init__(
|
||||
self,
|
||||
args: argparse.Namespace,
|
||||
scheduling_policy: Optional[SchedulingPolicy] = None,
|
||||
create_completion: Optional[Callable[[Request], StreamingResponse]] = None,
|
||||
create_chat_completion: Optional[Callable[[Request], StreamingResponse]] = None,
|
||||
scheduling_policy: SchedulingPolicy | None = None,
|
||||
create_completion: Callable[[Request], StreamingResponse] | None = None,
|
||||
create_chat_completion: Callable[[Request], StreamingResponse] | None = None,
|
||||
):
|
||||
self.validate_parsed_serve_args(args)
|
||||
self.port = args.port
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from typing import Any, Optional, Union
|
||||
from typing import Any
|
||||
|
||||
import msgspec
|
||||
import zmq
|
||||
@@ -25,16 +25,16 @@ class KVCacheEvent(
|
||||
|
||||
class BlockStored(KVCacheEvent):
|
||||
block_hashes: list[ExternalBlockHash]
|
||||
parent_block_hash: Optional[ExternalBlockHash]
|
||||
parent_block_hash: ExternalBlockHash | None
|
||||
token_ids: list[int]
|
||||
block_size: int
|
||||
lora_id: Optional[int]
|
||||
medium: Optional[str]
|
||||
lora_id: int | None
|
||||
medium: str | None
|
||||
|
||||
|
||||
class BlockRemoved(KVCacheEvent):
|
||||
block_hashes: list[ExternalBlockHash]
|
||||
medium: Optional[str]
|
||||
medium: str | None
|
||||
|
||||
|
||||
class AllBlocksCleared(KVCacheEvent):
|
||||
@@ -42,7 +42,7 @@ class AllBlocksCleared(KVCacheEvent):
|
||||
|
||||
|
||||
class KVEventBatch(EventBatch):
|
||||
events: list[Union[BlockStored, BlockRemoved, AllBlocksCleared]]
|
||||
events: list[BlockStored | BlockRemoved | AllBlocksCleared]
|
||||
|
||||
|
||||
def process_event(event_batch):
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
import asyncio
|
||||
from typing import Optional
|
||||
|
||||
from vllm.engine.arg_utils import AsyncEngineArgs
|
||||
from vllm.engine.async_llm_engine import AsyncLLMEngine
|
||||
@@ -43,7 +42,7 @@ async def main():
|
||||
)
|
||||
|
||||
prompt = "Who won the 2004 World Series?"
|
||||
final_output: Optional[RequestOutput] = None
|
||||
final_output: RequestOutput | None = None
|
||||
async for output in engine_client.generate(
|
||||
prompt=prompt,
|
||||
sampling_params=sampling_params,
|
||||
|
||||
@@ -8,8 +8,6 @@ Note that `pip install cohere` is needed to run this example.
|
||||
run: vllm serve BAAI/bge-reranker-base
|
||||
"""
|
||||
|
||||
from typing import Union
|
||||
|
||||
import cohere
|
||||
from cohere import Client, ClientV2
|
||||
|
||||
@@ -25,7 +23,7 @@ documents = [
|
||||
|
||||
|
||||
def cohere_rerank(
|
||||
client: Union[Client, ClientV2], model: str, query: str, documents: list[str]
|
||||
client: Client | ClientV2, model: str, query: str, documents: list[str]
|
||||
) -> dict:
|
||||
return client.rerank(model=model, query=query, documents=documents)
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ Refer to each `run_*` function for the command to run the server for that model.
|
||||
import argparse
|
||||
import base64
|
||||
import io
|
||||
from typing import Literal, Union
|
||||
from typing import Literal
|
||||
|
||||
from openai import OpenAI
|
||||
from openai._types import NOT_GIVEN, NotGiven
|
||||
@@ -29,7 +29,7 @@ def create_chat_embeddings(
|
||||
*,
|
||||
messages: list[ChatCompletionMessageParam],
|
||||
model: str,
|
||||
encoding_format: Union[Literal["base64", "float"], NotGiven] = NOT_GIVEN,
|
||||
encoding_format: Literal["base64", "float"] | NotGiven = NOT_GIVEN,
|
||||
) -> CreateEmbeddingResponse:
|
||||
"""
|
||||
Convenience function for accessing vLLM's Chat Embeddings API,
|
||||
|
||||
@@ -1,21 +1,15 @@
|
||||
# ruff: noqa: E501
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import enum
|
||||
import os
|
||||
from typing import TYPE_CHECKING, Any, Literal
|
||||
from typing import Any, Literal
|
||||
|
||||
import openai
|
||||
import pydantic
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from openai.types.chat import ChatCompletionChunk
|
||||
|
||||
from openai.types.chat import ChatCompletionChunk
|
||||
|
||||
ConstraintsFormat = Literal[
|
||||
"choice",
|
||||
|
||||
Reference in New Issue
Block a user