mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-31 11:56:44 +08:00
3754a9906d
* 支持稀疏attn * fix bug * code style * fix moba attn get kv shape * 修复a100编译 * codestyle * code style * code style * code style * fix conflict * 增加单侧 * code style * 增加eblite 加载时间 * fix bug * for ci * for ci * for ci * for ci * 支持mlp block size 128 * 增加小算子单测 * fix 单测 mlp * 将环境变量加入到config里面 * fix rollout config * 修复显存 * add test server * add test server * fix mlp 最后一层使用full attn
75 lines
2.6 KiB
Python
75 lines
2.6 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.
|
|
"""
|
|
|
|
import traceback
|
|
|
|
import paddle
|
|
|
|
from fastdeploy.utils import console_logger as logger
|
|
|
|
from .base import Platform, _Backend
|
|
|
|
|
|
class CUDAPlatform(Platform):
|
|
"""
|
|
cuda platform class
|
|
"""
|
|
|
|
device_name = "gpu"
|
|
|
|
@classmethod
|
|
def available(self):
|
|
"""
|
|
Check whether CUDA is available.
|
|
"""
|
|
try:
|
|
assert len(paddle.static.cuda_places()) > 0
|
|
return True
|
|
except Exception as e:
|
|
logger.warning(
|
|
"You are using GPU version PaddlePaddle, but there is no GPU "
|
|
"detected on your machine. Maybe CUDA devices is not set properly."
|
|
f"\n Original Error is {e}, "
|
|
f"{str(traceback.format_exc())}"
|
|
)
|
|
return False
|
|
|
|
@classmethod
|
|
def get_attention_backend_cls(cls, selected_backend: _Backend):
|
|
"""
|
|
get_attention_backend_cls
|
|
"""
|
|
if selected_backend == _Backend.NATIVE_ATTN:
|
|
logger.info("Using NATIVE ATTN backend.")
|
|
return "fastdeploy.model_executor.layers.attention.PaddleNativeAttnBackend"
|
|
elif selected_backend == _Backend.APPEND_ATTN:
|
|
logger.info("Using APPEND ATTN backend.")
|
|
return "fastdeploy.model_executor.layers.attention.AppendAttentionBackend"
|
|
elif selected_backend == _Backend.MLA_ATTN:
|
|
logger.info("Using MLA ATTN backend.")
|
|
return "fastdeploy.model_executor.layers.attention.MLAAttentionBackend"
|
|
elif selected_backend == _Backend.FLASH_ATTN:
|
|
logger.info("Using FLASH ATTN backend.")
|
|
return "fastdeploy.model_executor.layers.attention.FlashAttentionBackend"
|
|
elif selected_backend == _Backend.MOBA_ATTN:
|
|
logger.info("Using MOBA ATTN backend.")
|
|
return "fastdeploy.model_executor.layers.attention.MobaAttentionBackend"
|
|
else:
|
|
raise ValueError(
|
|
"Invalid attention backend you specified.\n"
|
|
"Now only support [NATIVE_ATTN, MLA_ATTN, APPEND_ATTN] in cuda place."
|
|
)
|