Commit 67d4a79

committed

Enables the per_tensor lowering patterns for weight per_packing

1 parent 5a50667 commit 67d4a79Copy full SHA for 67d4a79

2 files changed

+635

-5

lines changed

torchao/quantization/pt2e
- inductor_passes
  - arm.py
- quantizer
  - arm_inductor_quantizer.py

+635

-5

lines changed

Comments

(0)