mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-12 12:00:30 +08:00
434b48dda5
* [patchelf] fix patchelf error for inference xpu * [serving] add xpu dockerfile and support fd server * [serving] add xpu dockerfile and support fd server * [Serving] support XPU + Tritron * [Serving] support XPU + Tritron * [Dockerfile] update xpu tritron docker file -> paddle 0.0.0 * [Dockerfile] update xpu tritron docker file -> paddle 0.0.0 * [Dockerfile] update xpu tritron docker file -> paddle 0.0.0 * [Dockerfile] add comments for xpu tritron dockerfile * [Doruntime] fix xpu infer error * [Doruntime] fix xpu infer error * [XPU] update xpu dockerfile * add xpu triton server docs * add xpu triton server docs * add xpu triton server docs * add xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs * update xpu triton server docs
90 lines
2.3 KiB
Plaintext
90 lines
2.3 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: "inputs"
|
|
# 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, 224, 224 ]
|
|
}
|
|
]
|
|
|
|
# The output of the model is configured in the same format as the input
|
|
output [
|
|
{
|
|
name: "save_infer_model/scale_0.tmp_1"
|
|
data_type: TYPE_FP32
|
|
dims: [ 1000 ]
|
|
}
|
|
]
|
|
|
|
# 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
|
|
# kind: KIND_CPU
|
|
# The instance is deployed on the 0th GPU card
|
|
gpus: [0]
|
|
}
|
|
]
|
|
|
|
optimization {
|
|
execution_accelerators {
|
|
gpu_execution_accelerator : [ {
|
|
# use TRT engine
|
|
name: "tensorrt",
|
|
# use fp16 on TRT engine
|
|
parameters { key: "precision" value: "trt_fp16" }
|
|
},
|
|
{
|
|
name: "min_shape"
|
|
parameters { key: "inputs" value: "1 3 224 224" }
|
|
},
|
|
{
|
|
name: "opt_shape"
|
|
parameters { key: "inputs" value: "1 3 224 224" }
|
|
},
|
|
{
|
|
name: "max_shape"
|
|
parameters { key: "inputs" value: "16 3 224 224" }
|
|
}
|
|
]
|
|
}}
|
|
|
|
# instance_group [
|
|
# {
|
|
# # The number of instances is 1
|
|
# count: 1
|
|
# # Use GPU, CPU inference option is:KIND_CPU
|
|
# # kind: KIND_GPU
|
|
# kind: KIND_CPU
|
|
# # The instance is deployed on the 0th GPU card
|
|
# # gpus: [0]
|
|
# }
|
|
# ]
|
|
|
|
# optimization {
|
|
# execution_accelerators {
|
|
# cpu_execution_accelerator: [{
|
|
# name: "paddle_xpu",
|
|
# parameters { key: "cpu_threads" value: "4" }
|
|
# parameters { key: "use_paddle_log" value: "1" }
|
|
# parameters { key: "kunlunxin_id" value: "0" }
|
|
# parameters { key: "l3_workspace_size" value: "62914560" }
|
|
# parameters { key: "locked" value: "0" }
|
|
# parameters { key: "autotune" value: "1" }
|
|
# parameters { key: "precision" value: "int16" }
|
|
# parameters { key: "adaptive_seqlen" value: "0" }
|
|
# parameters { key: "enable_multi_stream" value: "0" }
|
|
# parameters { key: "gm_default_size" value: "0" }
|
|
# }]
|
|
# }} |