pytorch / pytorch/executorch

[Quantization Size Issue] Regarding the point at which the model size changes during quantization.

Open
#6,711 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: qnn need-user-input triaged
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

Hi @shewu-quic ~

Could you tell me after which method the actual physical size of the model reduces when we perform 8a8w quantization on the Llama-3.2-1B & 3B models using a QNN backend?

Thank you~!

cc @cccclai

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

The issue names 8a8w quantization, the QNN backend, and Llama-3.2-1B/3B models but no file or test. Start by tracing the QNN quantization flow and comparing model artifacts before and after each method; done would require a maintainer-confirmed explanation of when the physical size changes.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning, python
Domain
embedded-iot, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.