技术栈

大模型推理加速

hhhhhlt
6 个月前
论文阅读·代码大模型·量化压缩·大模型推理加速
【代码大模型】Compressing Pre-trained Models of Code into 3 MB论文阅读Compressing Pre-trained Models of Code into 3 MB key word: code PLM, compression, GA算法