mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-05-06 11:11:19 +08:00
567939953b
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Sage Moore <sage@neuralmagic.com> Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Signed-off-by: yewentao256 <zhyanwentao@126.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Co-authored-by: yewentao256 <zhyanwentao@126.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
20 lines
515 B
Python
20 lines
515 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from dataclasses import dataclass
|
|
|
|
from typing_extensions import TypeAlias
|
|
|
|
|
|
@dataclass
|
|
class UBatchSlice:
|
|
request_slice: slice
|
|
token_slice: slice
|
|
|
|
|
|
UBatchSlices: TypeAlias = list[UBatchSlice]
|
|
|
|
|
|
def is_second_ubatch_empty(orig_num_tokens_per_ubatch: int,
|
|
padded_num_tokens_per_ubatch: int) -> bool:
|
|
return padded_num_tokens_per_ubatch >= 2 * orig_num_tokens_per_ubatch
|