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:
Harry Mellor
2025-10-12 09:51:31 -07:00
committed by GitHub
parent 9bb38130cb
commit 8fcaaf6a16
944 changed files with 9490 additions and 10121 deletions
+6 -6
View File
@@ -10,7 +10,7 @@ on HuggingFace model repository.
import os
from dataclasses import asdict
from typing import Any, NamedTuple, Optional
from typing import Any, NamedTuple
from huggingface_hub import snapshot_download
from transformers import AutoTokenizer
@@ -30,11 +30,11 @@ question_per_audio_count = {
class ModelRequestData(NamedTuple):
engine_args: EngineArgs
prompt: Optional[str] = None
prompt_token_ids: Optional[dict[str, list[int]]] = None
multi_modal_data: Optional[dict[str, Any]] = None
stop_token_ids: Optional[list[int]] = None
lora_requests: Optional[list[LoRARequest]] = None
prompt: str | None = None
prompt_token_ids: dict[str, list[int]] | None = None
multi_modal_data: dict[str, Any] | None = None
stop_token_ids: list[int] | None = None
lora_requests: list[LoRARequest] | None = None
# NOTE: The default `max_num_seqs` and `max_model_len` may result in OOM on
@@ -3,7 +3,7 @@
# ruff: noqa: E501
import logging
from dataclasses import dataclass, field
from typing import TYPE_CHECKING, Optional
from typing import TYPE_CHECKING
from vllm.config import VllmConfig
from vllm.distributed.kv_transfer.kv_connector.v1.base import (
@@ -81,7 +81,7 @@ class RogueSharedStorageConnector(SharedStorageConnector):
def get_finished(
self, finished_req_ids: set[str]
) -> tuple[Optional[set[str]], Optional[set[str]]]:
) -> tuple[set[str] | None, set[str] | None]:
if self._async_load:
meta = self._get_connector_metadata()
assert isinstance(meta, RogueSharedStorageConnectorMetadata)
@@ -33,8 +33,6 @@ Output: ' in the hands of the people.\n\nThe future of AI is in the'
------------------------------------------------------------
"""
from typing import Optional
import torch
from vllm import LLM, SamplingParams
@@ -58,7 +56,7 @@ class DummyLogitsProcessor(LogitsProcessor):
def is_argmax_invariant(self) -> bool:
return False
def update_state(self, batch_update: Optional[BatchUpdate]):
def update_state(self, batch_update: BatchUpdate | None):
process_dict_updates(
self.req_info,
batch_update,
@@ -39,7 +39,7 @@ Output: ' in the hands of the people.\n\nThe future of AI is in the'
------------------------------------------------------------
"""
from typing import Any, Optional
from typing import Any
import torch
@@ -82,7 +82,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
def new_req_logits_processor(
self,
params: SamplingParams,
) -> Optional[RequestLogitsProcessor]:
) -> RequestLogitsProcessor | None:
"""This method returns a new request-level logits processor, customized
to the `target_token` value associated with a particular request.
@@ -96,7 +96,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
Returns:
`Callable` request logits processor, or None
"""
target_token: Optional[Any] = params.extra_args and params.extra_args.get(
target_token: Any | None = params.extra_args and params.extra_args.get(
"target_token"
)
if target_token is None:
@@ -41,8 +41,6 @@ which indicates that the logits processor is running. However, on a non-"cuda"
device, the first and third requests would not repeat the same token.
"""
from typing import Optional
import torch
from vllm import LLM, SamplingParams
@@ -91,7 +89,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
def new_req_logits_processor(
self,
params: SamplingParams,
) -> Optional[RequestLogitsProcessor]:
) -> RequestLogitsProcessor | None:
"""This method returns a new request-level logits processor, customized
to the `target_token` value associated with a particular request.
@@ -8,7 +8,6 @@ Requires HuggingFace credentials for access.
"""
import gc
from typing import Optional
import torch
from huggingface_hub import snapshot_download
@@ -19,7 +18,7 @@ from vllm.lora.request import LoRARequest
def create_test_prompts(
lora_path: str,
) -> list[tuple[str, SamplingParams, Optional[LoRARequest]]]:
) -> list[tuple[str, SamplingParams, LoRARequest | None]]:
return [
# this is an example of using quantization without LoRA
(
@@ -56,7 +55,7 @@ def create_test_prompts(
def process_requests(
engine: LLMEngine,
test_prompts: list[tuple[str, SamplingParams, Optional[LoRARequest]]],
test_prompts: list[tuple[str, SamplingParams, LoRARequest | None]],
):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
@@ -78,7 +77,7 @@ def process_requests(
def initialize_engine(
model: str, quantization: str, lora_repo: Optional[str]
model: str, quantization: str, lora_repo: str | None
) -> LLMEngine:
"""Initialize the LLMEngine."""
@@ -7,8 +7,6 @@ for offline inference.
Requires HuggingFace credentials for access to Llama2.
"""
from typing import Optional
from huggingface_hub import snapshot_download
from vllm import EngineArgs, LLMEngine, RequestOutput, SamplingParams
@@ -17,7 +15,7 @@ from vllm.lora.request import LoRARequest
def create_test_prompts(
lora_path: str,
) -> list[tuple[str, SamplingParams, Optional[LoRARequest]]]:
) -> list[tuple[str, SamplingParams, LoRARequest | None]]:
"""Create a list of test prompts with their sampling parameters.
2 requests for base model, 4 requests for the LoRA. We define 2
@@ -68,7 +66,7 @@ def create_test_prompts(
def process_requests(
engine: LLMEngine,
test_prompts: list[tuple[str, SamplingParams, Optional[LoRARequest]]],
test_prompts: list[tuple[str, SamplingParams, LoRARequest | None]],
):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
@@ -3,7 +3,6 @@
import argparse
import datetime
import os
from typing import Union
import albumentations
import numpy as np
@@ -160,7 +159,7 @@ def load_example(
file_paths: list[str],
mean: list[float] = None,
std: list[float] = None,
indices: Union[list[int], None] = None,
indices: list[int] | None = None,
):
"""Build an input example by loading images in *file_paths*.
+4 -3
View File
@@ -1,7 +1,8 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import gc
from typing import Callable, Optional, TypedDict
from collections.abc import Callable
from typing import TypedDict
import torch
import zmq
@@ -71,7 +72,7 @@ class WorkerExtension:
def rebuild_ipc(
handle: tuple[Callable, tuple], device_id: Optional[int] = None
handle: tuple[Callable, tuple], device_id: int | None = None
) -> torch.Tensor:
func, args = handle
list_args = list(args)
@@ -109,7 +110,7 @@ class ColocateWorkerExtension:
self._zmq_ctx = zmq.Context()
socket = self._zmq_ctx.socket(zmq.REP)
socket.connect(zmq_handles[self.report_device_id()])
buffer: Optional[torch.Tensor] = None
buffer: torch.Tensor | None = None
while True:
payload: tuple[Callable, tuple] | list[FlattenedTensorMetadata] | None = (
socket.recv_pyobj()
@@ -12,7 +12,7 @@ import os
import random
from contextlib import contextmanager
from dataclasses import asdict
from typing import NamedTuple, Optional
from typing import NamedTuple
from huggingface_hub import snapshot_download
from transformers import AutoTokenizer
@@ -28,8 +28,8 @@ from vllm.utils import FlexibleArgumentParser
class ModelRequestData(NamedTuple):
engine_args: EngineArgs
prompts: list[str]
stop_token_ids: Optional[list[int]] = None
lora_requests: Optional[list[LoRARequest]] = None
stop_token_ids: list[int] | None = None
lora_requests: list[LoRARequest] | None = None
# NOTE: The default `max_num_seqs` and `max_model_len` may result in OOM on
@@ -9,7 +9,7 @@ using the chat template defined by the model.
import os
from argparse import Namespace
from dataclasses import asdict
from typing import NamedTuple, Optional
from typing import NamedTuple
from huggingface_hub import snapshot_download
from PIL.Image import Image
@@ -41,9 +41,9 @@ class ModelRequestData(NamedTuple):
engine_args: EngineArgs
prompt: str
image_data: list[Image]
stop_token_ids: Optional[list[int]] = None
chat_template: Optional[str] = None
lora_requests: Optional[list[LoRARequest]] = None
stop_token_ids: list[int] | None = None
chat_template: str | None = None
lora_requests: list[LoRARequest] | None = None
# NOTE: The default `max_num_seqs` and `max_model_len` may result in OOM on
@@ -1251,7 +1251,7 @@ model_example_map = {
}
def run_generate(model, question: str, image_urls: list[str], seed: Optional[int]):
def run_generate(model, question: str, image_urls: list[str], seed: int | None):
req_data = model_example_map[model](question, image_urls)
engine_args = asdict(req_data.engine_args) | {"seed": args.seed}
@@ -1277,7 +1277,7 @@ def run_generate(model, question: str, image_urls: list[str], seed: Optional[int
print("-" * 50)
def run_chat(model: str, question: str, image_urls: list[str], seed: Optional[int]):
def run_chat(model: str, question: str, image_urls: list[str], seed: int | None):
req_data = model_example_map[model](question, image_urls)
# Disable other modalities to save memory
@@ -11,7 +11,7 @@ on HuggingFace model repository.
from argparse import Namespace
from dataclasses import asdict
from pathlib import Path
from typing import Literal, NamedTuple, Optional, TypedDict, Union, get_args
from typing import Literal, NamedTuple, TypeAlias, TypedDict, get_args
from PIL.Image import Image
@@ -47,15 +47,15 @@ class TextImagesQuery(TypedDict):
QueryModality = Literal["text", "image", "text+image", "text+images"]
Query = Union[TextQuery, ImageQuery, TextImageQuery, TextImagesQuery]
Query: TypeAlias = TextQuery | ImageQuery | TextImageQuery | TextImagesQuery
class ModelRequestData(NamedTuple):
engine_args: EngineArgs
prompt: Optional[str] = None
image: Optional[Image] = None
query: Optional[str] = None
documents: Optional[ScoreMultiModalParam] = None
prompt: str | None = None
image: Image | None = None
query: str | None = None
documents: ScoreMultiModalParam | None = None
def run_clip(query: Query) -> ModelRequestData:
@@ -281,7 +281,7 @@ def get_query(modality: QueryModality):
raise ValueError(msg)
def run_encode(model: str, modality: QueryModality, seed: Optional[int]):
def run_encode(model: str, modality: QueryModality, seed: int | None):
query = get_query(modality)
req_data = model_example_map[model](query)
@@ -311,7 +311,7 @@ def run_encode(model: str, modality: QueryModality, seed: Optional[int]):
print("-" * 50)
def run_score(model: str, modality: QueryModality, seed: Optional[int]):
def run_score(model: str, modality: QueryModality, seed: int | None):
query = get_query(modality)
req_data = model_example_map[model](query)