saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-20 19:12:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove redundant doc lines (#9946)

Browse source
This commit is contained in:
Hariharan Seshadri 2021-12-06 22:47:53 -08:00 committed by GitHub
parent fe3e672400
commit 70bd575cdd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/performance/tune-performance.md
View file

@ -288,10 +288,6 @@ ORT leverages CuDNN for convolution operations and the first step in this proces
providers = [("CUDAExecutionProvider", {"cudnn_conv_use_max_workspace": '1'})]
sess_options = ort.SessionOptions()
sess = ort.InferenceSession("my_conv_heavy_fp16_model.onnx", sess_options = sess_options, providers=providers)
options = sess.get_provider_options()
cuda_options = options['CUDAExecutionProvider']
cuda_options['cudnn_conv_use_max_workspace'] = '1'
sess.set_providers(['CUDAExecutionProvider'], [cuda_options])
```
* C/C++
Support for this provider option will be added in upcoming releases.