mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 09:07:10 +08:00
[LLM] First commit the llm deployment code
This commit is contained in:
65
fastdeploy/platforms/cuda.py
Normal file
65
fastdeploy/platforms/cuda.py
Normal file
@@ -0,0 +1,65 @@
|
||||
"""
|
||||
# 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.
|
||||
"""
|
||||
|
||||
"""
|
||||
cuda platform file
|
||||
"""
|
||||
|
||||
import paddle
|
||||
from .base import Platform, _Backend
|
||||
from paddlenlp.utils.log import logger
|
||||
|
||||
|
||||
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}"
|
||||
)
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def get_attention_backend_cls(
|
||||
cls,
|
||||
selected_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")
|
||||
else:
|
||||
logger.warning(
|
||||
"Other backends are not supported for now."
|
||||
)
|
Reference in New Issue
Block a user