biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Update deprecated Python 3.8 typing (#13971)

Browse Source
This commit is contained in:
Harry Mellor
2025-03-03 01:34:51 +00:00
committed by GitHub
parent bf33700ecd
commit cf069aa8aa
300 changed files with 2294 additions and 2347 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
vllm/v1/request.py
View File

@@ -1,7 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
import enum
from typing import TYPE_CHECKING, List, Optional, Union
from typing import TYPE_CHECKING, Optional, Union
from vllm.lora.request import LoRARequest
from vllm.sampling_params import SamplingParams
@@ -20,10 +20,10 @@ class Request:
self,
request_id: str,
prompt: Optional[str],
prompt_token_ids: List[int],
multi_modal_inputs: Optional[List["MultiModalKwargs"]],
multi_modal_hashes: Optional[List[str]],
multi_modal_placeholders: Optional[List["PlaceholderRange"]],
prompt_token_ids: list[int],
multi_modal_inputs: Optional[list["MultiModalKwargs"]],
multi_modal_hashes: Optional[list[str]],
multi_modal_placeholders: Optional[list["PlaceholderRange"]],
sampling_params: SamplingParams,
eos_token_id: Optional[int],
arrival_time: float,
@@ -36,7 +36,7 @@ class Request:
self.lora_request = lora_request
self.status = RequestStatus.WAITING
self.events: List[EngineCoreEvent] = []
self.events: list[EngineCoreEvent] = []
self.stop_reason: Union[int, str, None] = None
assert sampling_params.max_tokens is not None
self.max_tokens = sampling_params.max_tokens
@@ -44,15 +44,15 @@ class Request:
self.prompt = prompt
self.prompt_token_ids = prompt_token_ids
self.num_prompt_tokens = len(self.prompt_token_ids)
self._output_token_ids: List[int] = []
self._all_token_ids: List[int] = self.prompt_token_ids.copy()
self.spec_token_ids: List[int] = []
self._output_token_ids: list[int] = []
self._all_token_ids: list[int] = self.prompt_token_ids.copy()
self.spec_token_ids: list[int] = []
self.num_computed_tokens = 0
# Multi-modal related
self.mm_positions = multi_modal_placeholders or []
self.mm_inputs = multi_modal_inputs or []
self.mm_hashes: List[str] = multi_modal_hashes or []
self.mm_hashes: list[str] = multi_modal_hashes or []
# Sanity check
assert len(self.mm_inputs) == len(self.mm_positions)
@@ -89,7 +89,7 @@ class Request:
EngineCoreEvent.new_event(EngineCoreEventType.SCHEDULED,
timestamp))
def take_events(self) -> Optional[List[EngineCoreEvent]]:
def take_events(self) -> Optional[list[EngineCoreEvent]]:
if not self.events:
return None
events, self.events = self.events, []
@@ -97,7 +97,7 @@ class Request:
def append_output_token_ids(
self,
token_ids: Union[int, List[int]],
token_ids: Union[int, list[int]],
) -> None:
if isinstance(token_ids, int):
token_ids = [token_ids]