[LLM] First commit the llm deployment code

This commit is contained in:
jiangjiajun
2025-06-09 19:20:15 +08:00
parent 980c0a1d2c
commit 684703fd72
11814 changed files with 127294 additions and 1293102 deletions

View File

@@ -0,0 +1,30 @@
# 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.
""" setup for FASTDEPLOY base ops """
from paddle.utils.cpp_extension import setup, CppExtension
setup(
name="fastdeploy_base_ops",
ext_modules=CppExtension(
sources=[
"gpu_ops/save_with_output_msg.cc",
"gpu_ops/get_output.cc",
"gpu_ops/reset_need_stop_value.cc",
"gpu_ops/get_output_msg_with_topk.cc",
"gpu_ops/transfer_output.cc",
],
),
)