mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-11-01 04:12:58 +08:00
09bbac6de0
This tool allows you to compile all possible kernels in advance through the model's config.json, and avoids the situation where uncompiled kernel is encountered and JIT is executed when certain requests arrive.
31 lines
1.0 KiB
Bash
31 lines
1.0 KiB
Bash
# 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.
|
|
|
|
export PRE_COMPILE_LOG_LEVEL="INFO"
|
|
export DG_CACHE_DIR=$(pwd)/deep_gemm_cache
|
|
|
|
echo DeepGEMM Cache Dir: $DG_CACHE_DIR
|
|
|
|
MODEL_PATH=${1:-"/path/to/model"}
|
|
EXPERT_PARALLEL=${2:-"8"}
|
|
nproc=$(nproc)
|
|
|
|
python generate_config.py \
|
|
--model $MODEL_PATH \
|
|
--output=./deep_gemm_pre_compile_config.jsonl
|
|
|
|
python pre_compile.py \
|
|
--config_file=./deep_gemm_pre_compile_config.jsonl \
|
|
--expert_parallel=$EXPERT_PARALLEL \
|
|
--num_threads=$nproc |