This repository was archived by the owner on Sep 3, 2025. It is now read-only.

Release v0.7.0🚀

seungahdev released this 25 Sep 06:56

· 6 commits to main since this release

bac07a8

Further optimization for running FP8, and INT8 quantization.
Support searching automatic calibration dataset batch size for running FMO.
Support [AWQ(Activation-aware Weight Quantization)].

Assets 2