26 lines
1.2 KiB
Python
26 lines
1.2 KiB
Python
################################################################################
|
|
# Copyright(c)2020-2025 Shanghai Biren Technology Co., Ltd. All rights reserved.
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
################################################################################
|
|
|
|
# TODO(ychun) temp annotation
|
|
# @property # type: ignore
|
|
# def AttentionSpec_page_size_bytes(self) -> int:
|
|
# # For MLA we only store a single latent vector, BR166 uses BB, so it needs to be multiplied by 2
|
|
# coef = 1 if (self.use_mla and envs.VLLM_BR_DEVICE_SPC_NUM <= 16) else 2
|
|
# return coef * self.block_size * self.num_kv_heads * self.head_size \
|
|
# * get_dtype_size(self.dtype)
|
|
|
|
# AttentionSpec.page_size_bytes = AttentionSpec_page_size_bytes
|