Files
xc-llm-ascend/vllm_ascend/pool/__init__.py
Li Wang 30bf7014d0 [Bugfix] Add func swap_states to fix MLA attention (#1580)
### What this PR does / why we need it?
mla attention still using the gpu_input_batch's attr:`swap_states`, which will lead to
an error `AttributeError: 'InputBatch' object has no attribute 'swap_states'`

This PR fixed the mla input patch error
### How was this patch tested?
will be tested by #1136

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-07-02 17:42:53 +08:00

17 lines
672 B
Python

#
# Copyright (c) 2025 Huawei Technologies 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.
# This file is a part of the vllm-ascend project.
#