diff --git a/tests/benchdnn/inputs/graph/complex_fusion/harness_mha_all b/tests/benchdnn/inputs/graph/complex_fusion/harness_mha_all index 9cb4c804799..d96bd19e92b 100644 --- a/tests/benchdnn/inputs/graph/complex_fusion/harness_mha_all +++ b/tests/benchdnn/inputs/graph/complex_fusion/harness_mha_all @@ -45,6 +45,8 @@ --reset --dt=f32,bf16,f16 --in-shapes=0:acbd+1:acbd+8:acbd --case=complex_fusion/mha/sdpa-plain-simplified-f16.json --reset --dt=f32,bf16,f16 --in-shapes=3:384,3:384x384,3:1x16x384x384 --case=complex_fusion/mha/sdpa-plain-scale-by-mul-f16.json --reset --op-attrs=34107656704:group_shape:1x1x1x32+34107654464:transpose_b:1 --in-shapes=0:1x32x32x128+1:1x32x32x4+2:1x32x32x4 --case=complex_fusion/mha/sdpa-compressed-k-int8-gs32.json +--reset --op-attrs=34107656704:qtype:per_channel*axis:3 --in-shapes=1:32+2:1 --case=complex_fusion/mha/sdpa-compressed-k-int8-gs32.json +--reset --op-attrs=34107656704:qtype:per_channel*axis:2+34107654464:transpose_b:1 --in-shapes=0:1x32x32x128+1:32+2:1 --case=complex_fusion/mha/sdpa-compressed-k-int8-gs32.json # Re-written int8 graphs --reset --in-shapes=5:4x16x32x256+4:4x16x256x33+0:4x16x33x256+1:4x1x1x33+3:4x1x32x33 --case=complex_fusion/mha/MHA-GPT-inf-int8-bs1.json