Search help

Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.

Find an exact phrase: Wrap your search phrase in "" (double quotes) to only get results where the phrase is exactly matched. For example "PyTorch for the IPU" or "replicated tensor sharding"
Prefix query: Add an * (asterisk) at the end of any word to indicate a prefix query. This will return results containing all words with the specific prefix. For example tensor*

Fuzzy search: Use ~N (tilde followed by a number) at the end of any word for a fuzzy search. This will return results that are similar to the search word. N specifies the “edit distance” (fuzziness) of the match. For example Polibs~1
Words close to each other: ~N (tilde followed by a number) after a phrase (in quotes) returns results where the words are close to each other. N is the maximum number of positions allowed between matching words. For example "ipu version"~2
Logical operators. You can use the following logical operators in a search:
- + signifies AND operation
- | signifies OR operation
- - negates a single word or phrase (returns results without that word or phrase)
- () controls operator precedence

Running code on IPUs in Paperspace is no longer supported.

4. Quick start for Gradient Notebooks

There are three routes to use IPUs to run a Jupyter notebook on Paperspace Gradient:

From the Graphcore Model Garden
From the list of IPU-powered notebooks
From the setup procedure in this guide

Note

You will be required to sign into Paperspace before you can run any notebooks.

You can also access IPUs on Paperspace from VS Code with the setup described in the notebook Using VS Code in Paperspace Notebooks.

4.1. From the Graphcore Model Garden

Go to the Graphcore Model Garden.
Filter by “Paperspace”.
Click on Try on Paperspace for the notebook you want to run.
The notebook opens in Paperspace Gradient.
For example to run the notebook described in Section 6.2, Running the ViT model on a medical image dataset, filter by “Paperspace”, “PyTorch” and “Computer Vision” and click on Try on Paperspace:

_images/vit-model-garden.png — Fig. 4.1 Filter and click on Try on Paperspace from the Model Garden

4.2. From the list of IPU-powered notebooks

Go to the list of IPU-powered Jupyter Notebooks.
Click on Run on Gradient for the notebook you want to run.
The notebook opens in Paperspace Gradient.
For example to run the notebook described in Section 6.2, Running the ViT model on a medical image dataset, find the notebook and click on Run on Gradient:

_images/vit-notebook-list.png — Fig. 4.2 Find and click on Run on Gradient from the list of IPU-powered notebooks

4.3. From the setup procedure in this guide

Follow the procedure described in Section 5, Create a Gradient Notebook and try it out on the example notebook described in Section 6, Run a Jupyter notebook in a Gradient Notebook.