Closed yuwenzho closed 2 months ago
Warning If you do not have the access to re-run the Probot, please contact XuehaoSun for help. If you push a new commit, all of the workflow will be re-triggered.
Thank you for your contribution! 💜
Note This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact chensuyue or XuehaoSun for help.
Abstract WeightOnlyLinear class. Inherited class INCWeightOnlyLinear and HPUWeighOnlyLinear
For cpu, how does the woq algorithm use abstract class WeightOnlyLinear
? Do we use INCweightonlinear
instead of WeightOnlyLinear
?
Abstract WeightOnlyLinear class. Inherited class INCWeightOnlyLinear and HPUWeighOnlyLinear For cpu, how does the woq algorithm use abstract class
WeightOnlyLinear
? Do we useINCweightonlinear
instead ofWeightOnlyLinear
?
Yes, algorithm should use INCweightonlinear
. Fixed in https://github.com/intel/neural-compressor/pull/1877/commits/56c864f58cee53be0a79e816e5686bbe1fffbce1
Type of Change
feature API changed or not: no
Description
Use different WeightOnlyLinear module according to device.
load huggingface WOQ model example:
load INC WOQ model example:
How has this PR been tested?
CI
Dependency Change?
No