topic KV Cache offloading in AI in ONTAP Discussions

topic KV Cache offloading in AI in ONTAP Discussions https://community.netapp.com/t5/ONTAP-Discussions/KV-Cache-offloading-in-AI/m-p/460170#M44895 <P>Hi, Expert,</P><P> </P><P>      Weka mentioned they had AI KV Cache offloading fuction/solution called AMG (augmented memory grid).  I'm not sure it's new or just  decoration based on GDS.   Can ONTAP do KV Cache offloading or  is it just the capability from GDS stack ?</P><P> </P><P>    Rgds,</P><P>    Jackie</P> Thu, 17 Apr 2025 08:08:42 GMT Jackiez 2025-04-17T08:08:42Z KV Cache offloading in AI https://community.netapp.com/t5/ONTAP-Discussions/KV-Cache-offloading-in-AI/m-p/460170#M44895 <P>Hi, Expert,</P><P> </P><P>      Weka mentioned they had AI KV Cache offloading fuction/solution called AMG (augmented memory grid).  I'm not sure it's new or just  decoration based on GDS.   Can ONTAP do KV Cache offloading or  is it just the capability from GDS stack ?</P><P> </P><P>    Rgds,</P><P>    Jackie</P> Thu, 17 Apr 2025 08:08:42 GMT https://community.netapp.com/t5/ONTAP-Discussions/KV-Cache-offloading-in-AI/m-p/460170#M44895 Jackiez 2025-04-17T08:08:42Z