NVIDIA / NVIDIA/Model-Optimizer

Why int4 quant use special data size setting ?

Open
#1,539 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.8k
Forks
604
Avg merge
2d 8h
Merged PRs (30d)
142

Description

https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/onnx_ptq#prepare-calibration-data

For Int4 quantization, it is recommended to set --calibration_data_size=64.

Why int4 quant use special data size setting ?

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 with the linked examples/onnx_ptq documentation and the “prepare calibration data” section. Trace where --calibration_data_size is used for Int4 quantization and confirm what explanation the documentation should provide. Done means the reason for the value 64 is documented clearly in the relevant example or guide.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.