[Perf] Optimize Python Slice for Structured Output using islice instead of [:] (#33593)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Wentao Ye
2026-02-24 09:02:36 -08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent c38b8d5a31
commit 9ce8fad2a9
8 changed files with 23 additions and 16 deletions
+6 -3
View File
@@ -1,7 +1,8 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Sequence
from collections.abc import Iterable, Sequence
from itertools import islice
import regex as re
from transformers import PreTrainedTokenizerBase
@@ -104,13 +105,15 @@ class Step3ReasoningParser(ReasoningParser):
return self.think_end_token_id in input_ids
def is_reasoning_end_streaming(
self, input_ids: Sequence[int], delta_ids: Sequence[int]
self, input_ids: Sequence[int], delta_ids: Iterable[int]
) -> bool:
end_token_id = self.think_end_token_id
return end_token_id in delta_ids
def extract_content_ids(self, input_ids: list[int]) -> list[int]:
if self.think_end_token_id not in input_ids[:-1]:
if self.think_end_token_id not in islice(
input_ids, 0, max(0, len(input_ids) - 1)
):
return []
else:
return input_ids[input_ids.index(self.think_end_token_id) + 1 :]