[Kernel] SM120: stop routing misaligned-M blockwise FP8 GEMMs to the small-M swapAB config (#52775)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
This commit is contained in:
+1
-1
@@ -250,7 +250,7 @@ void cutlass_gemm_blockwise_sm120_fp8_dispatch(torch::stable::Tensor& out,
|
||||
torch::stable::Tensor const& b_scales) {
|
||||
int M = a.size(0);
|
||||
// more heuristic tuning can be done here by checking N/K dimensions as well
|
||||
bool swap_ab = (M <= 64) || (M % 4 != 0);
|
||||
bool swap_ab = (M <= 64);
|
||||
|
||||
if (!swap_ab) {
|
||||
if (M <= 256) {
|
||||
|
||||
Reference in New Issue
Block a user