5c33a8289b
* ResNet50/PyT Triton ONNXruntime fix with env flag Scripts were modified to fix missing ORT_TENSORRT_FP16_ENABLE flag for Triton Inference Server with ONNXRuntime and TensorRT execution provider. * ResNet50/PyT TensorRT FP16 support fixed ONNX to TensorRT converter was fixed to force FP16 precision for TensorRT networks.
24 lines
894 B
Bash
Executable file
24 lines
894 B
Bash
Executable file
#!/usr/bin/env bash
|
|
# Copyright (c) 2021 NVIDIA CORPORATION. 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 PRECISION="fp16"
|
|
export FORMAT="onnx"
|
|
export BATCH_SIZE="1,2,4,8,16,32,64,128"
|
|
export BACKEND_ACCELERATOR="trt"
|
|
export MAX_BATCH_SIZE="128"
|
|
export NUMBER_OF_MODEL_INSTANCES="1"
|
|
export TRITON_MAX_QUEUE_DELAY="1"
|
|
export TRITON_PREFERRED_BATCH_SIZES="64 128"
|
|
|