diff --git a/example/01_gemm/gemm_xdl_fp8_pk_i4_bpreshuffle_v3.cpp b/example/01_gemm/gemm_xdl_fp8_pk_i4_bpreshuffle_v3.cpp index 0de47d16a3..712c6c6273 100644 --- a/example/01_gemm/gemm_xdl_fp8_pk_i4_bpreshuffle_v3.cpp +++ b/example/01_gemm/gemm_xdl_fp8_pk_i4_bpreshuffle_v3.cpp @@ -36,16 +36,16 @@ using DeviceGemmV2Instance = ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CElementOp, GemmDefault, - 128, - 16, 128, + 256, + 128, 128, KPerBlock, 16, 32, - 16, 16, - 1, 4, - S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, + 32, 32, + 4, 1, + S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, - S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, + S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 32, 32, 0, - 1, 1, S<1, 16, 1, 8>, 4, + 1, 1, S<1, 32, 1, 8>, 4, ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1, F8, F8, PermuteA, PermuteB>; // clang-format on