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

5.1. Passes

A pass is a component used to optimise an ONNX model in PopRT. To create a custom pass, see the Custom passes section.

5.1.1. Pass abstract

Passes in PopRT are all inherited from poprt.Pass.

Passes are auto-registered. All registered passes can be listed with the following CLI command:

poprt --list_all_passes

or in Python with:

import poprt

passes = poprt.get_registered_passes()
print(passes.keys())

Use the Python poprt.Pass.get_pass() function to get a pass by its registered name (see Built-in passes for the registered names of built-in passes). You can also use poprt.PassManager to apply multiple passes.

Note

Since the structure of the poprt.passes module may change, the following instructions are not recommended:

from poprt.passes.float_to_half import Float2Half

Float2Half()(onnx_model)