mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
f0f00a6025
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
* delete nonzero * delete setup_ops_base.py * check if * check gcp infer_seed.cpu() * fix repetition_early_stopper_kernel cuda 700
24 lines
935 B
Python
24 lines
935 B
Python
# Copyright (c) 2024 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.
|
|
"""fastdeploy gpu ops"""
|
|
|
|
from fastdeploy.import_ops import import_custom_ops
|
|
|
|
PACKAGE = "fastdeploy.model_executor.ops.iluvatar"
|
|
|
|
import_custom_ops(PACKAGE, ".fastdeploy_ops", globals())
|
|
|
|
from .moe_ops import iluvatar_moe_expert_ffn as moe_expert_ffn # noqa: F401
|
|
from .paged_attention import paged_attention # noqa: F401
|