D1: Fix kvb→kvh typo in PV GEMM

This commit is contained in:
2026-05-24 06:41:25 +00:00
parent e2b914be5e
commit f2170fc1b3

View File

@@ -263,11 +263,11 @@ class FmhaKernel:
pv_mma.set(tcgen05.Field.ACCUMULATE, kt != 0)
if not self.use_smem_p:
for kb in cutlass.range(cute.size(tOrP0, mode=[2]), unroll_full=True):
cute.gemm(pv_mma, tOtO0, tOrP0[(None,None,kb)], tCrV[(None,None,kvb.index)], tOtO0)
cute.gemm(pv_mma, tOtO0, tOrP0[(None,None,kb)], tCrV[(None,None,kb,kvh.index)], tOtO0)
pv_mma.set(tcgen05.Field.ACCUMULATE, True)
else:
for kb in cutlass.range(cute.size(tCrP, mode=[2]), unroll_full=True):
cute.gemm(pv_mma, tOtO0, tCrP[(None,None,kb,0)], tCrV[(None,None,kvb.index)], tOtO0)
cute.gemm(pv_mma, tOtO0, tCrP[(None,None,kb,0)], tCrV[(None,None,kb,kvh.index)], tOtO0)
pv_mma.set(tcgen05.Field.ACCUMULATE, True)
cute.arch.fence_view_async_tmem_store()
final_o_bar.arrive()