search

PaddlePaddle / PaddleSlim

PaddleSlim is an open-source library for deep model compression and architecture search.
https://paddleslim.readthedocs.io/zh_CN/latest/
Apache License 2.0
1.56k stars 345 forks source link

Add new observer for KVCache and FP8 quantization #1902

Closed lixcli closed 3 days ago

lixcli commented 3 days ago

Add new observer for KVCache and FP8 quantization

paddle-bot[bot] commented 3 days ago

Thanks for your contribution!

CLAassistant commented 3 days ago

CLA assistant check
All committers have signed the CLA.