[Kernel] Add b12x FP4 MoE backend (#52018)

Signed-off-by: Luke Alonso <lalonso@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Luke Alonso
2026-08-21 08:04:36 -07:00
committed by GitHub
co-authored by mgoin
parent 5ee84d3c52
commit 2740c817ff
23 changed files with 2417 additions and 60 deletions
@@ -1574,6 +1574,7 @@ class ModelOptNvFp4FusedMoE(FusedMoEMethodBase):
w2_scale_2=layer.w2_weight_scale_2,
a2_scale=layer.w2_input_scale,
is_act_and_mul=self.moe.is_act_and_mul,
use_a16=self.use_a16,
)
replace_parameter(layer, "w13_weight", w13)
@@ -1610,6 +1611,7 @@ class ModelOptNvFp4FusedMoE(FusedMoEMethodBase):
swiglu_alpha=getattr(layer, "swiglu_alpha", None),
swiglu_beta=getattr(layer, "swiglu_beta", None),
layer=layer,
use_a16=self.use_a16,
)
@property