mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
yzwu
36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
# Copyright (c) 2025 PaddlePaddle Authors. 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.
|
|
|
|
from fastdeploy.utils import console_logger as logger
|
|
|
|
from .base import Platform, _Backend
|
|
|
|
|
|
class IluvatarPlatform(Platform):
|
|
device_name = "iluvatar_gpu"
|
|
|
|
@classmethod
|
|
def get_attention_backend_cls(cls, selected_backend):
|
|
"""
|
|
get_attention_backend_cls
|
|
"""
|
|
if selected_backend == _Backend.APPEND_ATTN:
|
|
logger.info("Using ixinfer MHA backend instead of append attention")
|
|
return "fastdeploy.model_executor.layers.backends.iluvatar.MhaAttnBackend"
|
|
else:
|
|
raise ValueError(
|
|
"Invalid attention backend you specified.\n"
|
|
"Now only support [NATIVE_ATTN, MLA_ATTN, APPEND_ATTN] in cuda place."
|
|
)
|