https://blog.youkuaiyun.com/zhjunqinzh-cnhttps://blog.youkuaiyun.com/https://blog.youkuaiyun.com/zhjunqin/article/details/135727095https://blog.youkuaiyun.com/zhjunqin/article/details/135727095zhjunqinSun, 21 Jan 2024 12:20:03 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/135587979https://blog.youkuaiyun.com/zhjunqin/article/details/135587979zhjunqinSun, 14 Jan 2024 21:48:46 +0800 GPU 共享内存，因此量化显著减少了数据的传输量，提高了整体效率。AWQ 算法全称：Activation-aware Weight Quantization。]]>https://blog.youkuaiyun.com/zhjunqin/article/details/135572684https://blog.youkuaiyun.com/zhjunqin/article/details/135572684zhjunqinSun, 14 Jan 2024 10:59:16 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/135491992https://blog.youkuaiyun.com/zhjunqin/article/details/135491992zhjunqinWed, 10 Jan 2024 23:13:34 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/135433000https://blog.youkuaiyun.com/zhjunqin/article/details/135433000zhjunqinSat, 06 Jan 2024 22:34:34 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/135397770https://blog.youkuaiyun.com/zhjunqin/article/details/135397770zhjunqinThu, 04 Jan 2024 23:07:47 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/130978583https://blog.youkuaiyun.com/zhjunqin/article/details/130978583zhjunqinWed, 31 May 2023 22:52:37 +0800https://blog.youkuaiyun.com/zhjunqin/article/details/130962288https://blog.youkuaiyun.com/zhjunqin/article/details/130962288zhjunqinWed, 31 May 2023 09:36:01 +0800