0 0 1 Python

Qualcomm AI Engine Direct - refactor quantizer (#1339)

Summary:
- Refactor qnn quantizer
- Add 16bits default quantization setting

Pull Request resolved: https://github.com/pytorch/executorch/pull/1339

Reviewed By: kimishpatel, jerryzh168

Differential Revision: D51824122

Pulled By: cccclai

fbshipit-source-id: 502d812e82ca45f512042fe550c71365a4beaf76

chunit-quic committed 2y ago

dbcdce2d2f2467c90d9dc2784e0eef8f847381f5

Parent: abc0ddc

Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> on 12/7/2023, 5:06:39 AM