diff --git a/dsv4/kernels/attention/fmha.py b/dsv4/kernels/attention/fmha.py index c2edf2ca..787cf426 100644 --- a/dsv4/kernels/attention/fmha.py +++ b/dsv4/kernels/attention/fmha.py @@ -47,7 +47,7 @@ class FmhaKernel: self.k_smem_s = utils.sm100.make_smem_layout_b(qk_mma, self.qk_mma_tiler, self.q_dtype, self.kv_stage) self.v_smem_s = utils.sm100.make_smem_layout_b(pv_mma, self.pv_mma_tiler, self.q_dtype, self.kv_stage) self.p_smem_s = utils.sm100.make_smem_layout_a(pv_mma, self.pv_mma_tiler, self.q_dtype, 1) - self.c_smem_s = utils.sm100.make_epilogue_smem_layout(self.o_dtype, self.c_layout, self.epi_tile, 2) + self.c_smem_s = utils.sm100.make_smem_layout_epi(self.o_dtype, self.c_layout, self.epi_tile, 2) # TMEM: only S (QK result). P is in SMEM, O also in TMEM. qk_thr = qk_mma.get_slice(0); qk_as = qk_thr.partition_shape_C(self.qk_mma_tiler[:2]) tStS = qk_thr.make_fragment_C(qk_as)