Add quantization documentation to vulkan docs
Open
@SS-JIA is already working on this.
Since Jul 8, 2025.
module: vulkan
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
The Vulkan backend docs do not discuss how to do quantization: https://github.com/pytorch/executorch/blob/main/docs/source/backends-vulkan.md
From the backend-template, the quantization section should document how to quantize a model and go over the available quantization configs: https://github.com/pytorch/executorch/blob/main/docs/source/backend-template.md#quantization
See examples for XNNPACK and CoreML.
Once the section is filled out, add a link to the quantization overview page.
If Vulkan does not currently support quantization, feel free to close this task
cc @SS-JIA @manuelcandales @cbilgin
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.