Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update gpu_model_example.md #8

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update gpu_model_example.md #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/2_model_setup/gpu_model_example.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@

UIF accelerates deep learning inference applications on all AMD compute platforms for popular machine learning frameworks, including TensorFlow, PyTorch, and ONNXRT. UIF 1.2 extends the support to AMD Radeon™ GPUs in addition to AMD Instinct™ GPUs. Currently, [MIGraphX](https://github.com/ROCmSoftwarePlatform/AMDMIGraphX) is the acceleration library for Deep Learning Inference running on AMD Instinct GPUs.

The following example takes a PyTorch ResNet-50-v1.5 model selected from UIF Model Zoo as an example to show how it works on different GPU platforms.
The following example takes a [PyTorch ResNet-50-v1.5 model](https://github.com/amd/UIF/blob/main/docs/2_model_setup/model-list/pt_resnet50v1.5_1.1_M2.6/model.yaml) selected from UIF Model Zoo as an example to show how it works on different GPU platforms.

**Note:** The model tuning time on a MI210 device is long (around three hours). With MI210, it is recommended to skip this step and use the YModel provided in the model packages.

Expand Down