Fixed Optimum link to point to published doc page
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ execution provider (EP) for ONNX Runtime combined with quantization tools and a
|
|
| 22 |
All of this is made possible based on Ryzen™ AI technology built on AMD XDNA™ architecture,
|
| 23 |
purpose-built to run AI workloads efficiently and locally,
|
| 24 |
offering a host of benefits for the developer innovating the next groundbreaking AI app. Details on getting started
|
| 25 |
-
with Hugging Face models are available on the [Optimum page](https://
|
| 26 |
|
| 27 |
The following section describes how to use the most common transformers on Hugging Face
|
| 28 |
for inference workloads on select AMD Instinct™ accelerators and AMD Radeon™ GPUs using the AMD ROCm software ecosystem.
|
|
|
|
| 22 |
All of this is made possible based on Ryzen™ AI technology built on AMD XDNA™ architecture,
|
| 23 |
purpose-built to run AI workloads efficiently and locally,
|
| 24 |
offering a host of benefits for the developer innovating the next groundbreaking AI app. Details on getting started
|
| 25 |
+
with Hugging Face models are available on the [Optimum page](https://huggingface.co/docs/optimum/main/en/amd/index)
|
| 26 |
|
| 27 |
The following section describes how to use the most common transformers on Hugging Face
|
| 28 |
for inference workloads on select AMD Instinct™ accelerators and AMD Radeon™ GPUs using the AMD ROCm software ecosystem.
|