[Bugfix][CPU] Fix DeepSeek-R1 (FP8 MLA + MoE) correctness on CPU backend (#56773)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
@@ -468,6 +468,7 @@ class CPUExpertsFp8(mk.FusedMoEExpertsModular):
|
||||
RoutingMethodType.Renormalize,
|
||||
RoutingMethodType.RenormalizeNaive,
|
||||
RoutingMethodType.DeepseekV4,
|
||||
RoutingMethodType.DeepSeekV3,
|
||||
]
|
||||
|
||||
@staticmethod
|
||||
|
||||
Reference in New Issue
Block a user