SIGN IN SIGN UP

Qualcomm AI Engine Direct - Set llama io as quantized tensor (#5383)

* Qualcomm AI Engine Direct - Add llama io be quantized

- Add general function to tag io obtain/genetate quantized tensor
- Add quantizing io function to llama2.py

* [Fix lint]

---------

Co-authored-by: Joey Tsai <chunit@qti.qualcomm.com>
C
Chun-I Tsai committed
b2f73a34419dfa0bce7c3771701a56dfb7cf7fee
Parent: 16b633b
Committed by GitHub <noreply@github.com> on 10/28/2024, 3:53:17 PM