apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Backend] Add pybind & PaddleDetection example for TVM (#1998)

Browse Source 
* update

* update

* Update infer_ppyoloe_demo.cc

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
This commit is contained in:
Zheng-Bicheng
2023-06-04 13:26:47 +08:00
committed by GitHub
parent c634a9260d
commit 8d357814e8
10 changed files with 189 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
python/fastdeploy/runtime.py
View File

@@ -244,10 +244,9 @@ class RuntimeOption:
:param enable_multi_stream: (bool)Whether to enable the multi stream of KunlunXin XPU.
:param gm_default_size The default size of context global memory of KunlunXin XPU.
"""
return self._option.use_kunlunxin(device_id, l3_workspace_size, locked,
autotune, autotune_file, precision,
adaptive_seqlen, enable_multi_stream,
gm_default_size)
return self._option.use_kunlunxin(
device_id, l3_workspace_size, locked, autotune, autotune_file,
precision, adaptive_seqlen, enable_multi_stream, gm_default_size)
def use_cpu(self):
"""Inference with CPU
@@ -271,7 +270,7 @@ class RuntimeOption:
def disable_valid_backend_check(self):
""" Disable checking validity of backend during inference
"""
"""
return self._option.disable_valid_backend_check()
def enable_valid_backend_check(self):
@@ -316,6 +315,11 @@ class RuntimeOption:
"""
return self._option.use_ort_backend()
def use_tvm_backend(self):
"""Use TVM Runtime backend, support inference TVM model on CPU.
"""
return self._option.use_tvm_backend()
def use_trt_backend(self):
"""Use TensorRT backend, support inference Paddle/ONNX model on Nvidia GPU.
"""