mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-31 03:46:40 +08:00
d57e997fa0
* fd serving add dockerfile * fix enable_paddle_mkldnn * delete disable_paddle_mkldnn Co-authored-by: Jason <jiangjiajun@baidu.com>
47 lines
1.1 KiB
Plaintext
47 lines
1.1 KiB
Plaintext
# optional, If name is specified it must match the name of the model repository directory containing the model.
|
||
name: "runtime"
|
||
backend: "fastdeploy"
|
||
max_batch_size: 16
|
||
|
||
# Input configuration of the model
|
||
input [
|
||
{
|
||
# input name
|
||
name: "images"
|
||
# input type such as TYPE_FP32、TYPE_UINT8、TYPE_INT8、TYPE_INT16、TYPE_INT32、TYPE_INT64、TYPE_FP16、TYPE_STRING
|
||
data_type: TYPE_FP32
|
||
# input shape， The batch dimension is omitted and the actual shape is [batch, c, h, w]
|
||
dims: [ 3, -1, -1 ]
|
||
}
|
||
]
|
||
|
||
# The output of the model is configured in the same format as the input
|
||
output [
|
||
{
|
||
name: "output"
|
||
data_type: TYPE_FP32
|
||
dims: [ -1, -1 ]
|
||
}
|
||
]
|
||
|
||
# Number of instances of the model
|
||
instance_group [
|
||
{
|
||
# The number of instances is 1
|
||
count: 1
|
||
# Use GPU, CPU inference option is:KIND_CPU
|
||
kind: KIND_GPU
|
||
# The instance is deployed on the 0th GPU card
|
||
gpus: [0]
|
||
}
|
||
]
|
||
|
||
optimization {
|
||
execution_accelerators {
|
||
gpu_execution_accelerator : [ {
|
||
# use ONNXRuntime engine
|
||
name: "onnxruntime",
|
||
parameters { key: "cpu_threads" value: "2" }
|
||
}]
|
||
}}
|