search

quic / aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
https://quic.github.io/aimet-pages/index.html
Other
2.15k stars 383 forks source link

Optimize quantization functions with torch.compile #3336

Closed quic-kyunggeu closed 2 months ago

quic-kyunggeu commented 2 months ago

Added **experimental** support for torch.compile.