[https://nvbugs/5284463][fix] fix ada fp8 group gemm lacks shared memory (NVIDIA#9044)

Signed-off-by: Vincent Zhang <vinczhang@nvidia.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>

Author: inocsin

cpp/tensorrt_llm/kernels/cutlass_kernels/cutlass_heuristic.cpp

@@ -177,13 +177,13 @@ std::vector<CutlassTileConfig> get_candidate_tiles(
         {
             if (sm == 89 || sm >= 120)
             {
-                return {CutlassTileConfig::CtaShape16x256x128_WarpShape16x64x128,
-                    CutlassTileConfig::CtaShape32x128x64_WarpShape32x32x64,
+                return {CutlassTileConfig::CtaShape32x128x64_WarpShape32x32x64,
                     CutlassTileConfig::CtaShape64x128x64_WarpShape64x32x64,
                     CutlassTileConfig::CtaShape64x64x128_WarpShape32x64x64,
                     CutlassTileConfig::CtaShape128x64x64_WarpShape64x32x64,
                     CutlassTileConfig::CtaShape128x256x64_WarpShape64x64x64,
-                    CutlassTileConfig::CtaShape256x128x64_WarpShape64x64x64};
+                    CutlassTileConfig::CtaShape256x128x64_WarpShape64x64x64,
+                    CutlassTileConfig::CtaShape16x256x128_WarpShape16x64x128};
             }
             else
             {