onnx / onnx/models

Quantized model test data on GPU

Open
#581 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Ask a Question

Since the GPU machines of CI have been upgraded from NV6 to T4, it looks quantized model on GPU should be added too.
Hardware support is required to achieve better performance with quantization on GPUs. You need a device that supports Tensor Core int8 computation, like T4 or A100.
https://onnxruntime.ai/docs/performance/quantization.html#quantization-on-gpu

But it looks that the test result on CPU with VNNI if different from on GPU. Is it expected? @yufenglee
If it's expected, shall we add test data on GPU? @jcwchen @snnn

Contributor guide

No contributing guide indexed for this repository

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

Review the ONNX Runtime quantization-on-GPU documentation and the linked Azure Pipelines test result first, then compare the CPU/VNNI and T4 outcomes. Done means establishing whether the difference is expected and deciding whether GPU-specific quantized-model test data should be added.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning, testing
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.