[Fix][Compile] Declare group_shape in the static FP8 quant fusion … (#61108)
Signed-off-by: Laith Sakka <lsakka@meta.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
c599b5971f
commit
12e6a585ae
@@ -481,8 +481,13 @@ class MatcherQuantFP8(MatcherCustomOp):
|
|||||||
|
|
||||||
if self.quant_key.scale.static:
|
if self.quant_key.scale.static:
|
||||||
assert scale is not None
|
assert scale is not None
|
||||||
|
group_shape = self.quant_key.scale.group_shape
|
||||||
_, result = auto_functionalized(
|
_, result = auto_functionalized(
|
||||||
self.QUANT_OP, result=result, input=input, scale=scale
|
self.QUANT_OP,
|
||||||
|
result=result,
|
||||||
|
input=input,
|
||||||
|
scale=scale,
|
||||||
|
group_shape=[group_shape.row, group_shape.col],
|
||||||
)
|
)
|
||||||
return result, scale
|
return result, scale
|
||||||
else:
|
else:
|
||||||
|
|||||||
Reference in New Issue
Block a user