pytorch / pytorch/executorch

Enable MobileBert and Albert with XNNPACK quantization

Open
#12,341 4 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

module: xnnpack
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

Currently quantization in CI is disabled for MobileBert and Albert

Here's the error code: https://gist.github.com/mergennachin/2abc5cae46925abdb9fc582b1c520159

cc @digantdesai @mcr229 @cbilgin

Internal task: T197452682

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the CI quantization configuration for MobileBert and Albert, then examine the linked error report to identify why XNNPACK quantization is disabled. Done means both models complete the quantization CI path without the reported error; no specific files or tests are named in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ci-cd, machine-learning, mobile-dev
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.