IPEX support FP8 kvcache/softcap/slidingwindow (#3144)
* IPEX support FP8 kvcache Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * add kvcache dtype Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * add softcap and slidingwindow Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * kv scale in pageattn Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * remove triton installation, will be installed with torch Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * install xelink lib Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * softcap default -1.0 Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * softcap default -1.0 Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> --------- Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
W
Wang, Yi committed
51a0b9d11c27b4a80c185d7f8333c0a63f54f6fd
Parent: f208ba6
Committed by GitHub <noreply@github.com>
on 5/6/2025, 8:49:24 AM