Skip to content

GitLab

Commit 660261a2 authored by Qianfeng Zhang's avatar Qianfeng Zhang
Browse files

Adjust the using of kPadSeqLenQ and kPadSeqLenK in the kernel

parent aa304c67
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
include/ck_tile/ops/fmha/kernel/fmha_fwd_kernel.hpp
View file @ 660261a2
......@@ -1064,14 +1064,14 @@ struct FmhaFwdKernel
return pad_tensor_view(
q_dram_naive,
make_tuple(number<FmhaPipeline::kM0>{}, number<FmhaPipeline::kSubQKHeaddim>{}),
sequence<false, kPadHeadDimQ>{});
sequence<kPadSeqLenQ, kPadHeadDimQ>{});
}
else
{
return pad_tensor_view(
q_dram_naive,
make_tuple(number<FmhaPipeline::kM0>{}, number<FmhaPipeline::kK0>{}),
sequence<false, kPadHeadDimQ>{});
sequence<kPadSeqLenQ, kPadHeadDimQ>{});
}
}();
const auto k_dram = [&]() {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment