CUDA support for the Quantization routines
Status | Pipeline | Created by | Stages | |
---|---|---|---|---|
Failed 00:29:40
| Stage: static_analysis Stage: build Stage: test Stage: coverage Stage: release | No artifacts found | ||
This MR introduces the CUDA support for the PTQ and QAT routines.
For the Quantization module, it is a game changer as it now allows to quantize real size models (e.g. ResNet18) in only few minutes instead of several hours.
Regarding the QAT, minor modifications were also made to make it functional, but for now the QAT is only working over small sized models.
Here is an exhaustive list of the changes made to the source files :
This MR does not fully enable the QAT, which for now only works over small models/datasets.
Later works will also provide unit tests for the QAT.
Status | Pipeline | Created by | Stages | |
---|---|---|---|---|
Failed 00:29:40
| Stage: static_analysis Stage: build Stage: test Stage: coverage Stage: release |
Download artifacts
No artifacts found | ||
0 |
Copyright © Eclipse Foundation, Inc. All Rights Reserved. Privacy Policy | Terms of Use | Copyright Agent