diff --git a/include/ck_tile/ops/gemm/warp/warp_gemm.hpp b/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
index a2c320f3e6..a7695af409 100644
--- a/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
@@ -378,18 +378,34 @@ using WarpGemmMfma_f32_32x32x16_fp8_fp8_CTransposed =
     WarpGemmImpl<WarpGemmAttributeMfmaTransposedCDistribution<
         WarpGemmAttributeMfmaImpl_f32_32x32x16_fp8_fp8<WGAttrCtlEnum::Default_>>>;
 
+using WarpGemmMfma_f32_32x32x32_fp8_fp8_CTransposed = WarpGemmImpl<WarpGemmAttributeMfmaIterateK<
+    WarpGemmAttributeMfmaImpl_f32_32x32x16_fp8_fp8<WGAttrCtlEnum::Default_>,
+    2>>;
+
 using WarpGemmMfma_f32_32x32x16_fp8_bf8_CTransposed =
     WarpGemmImpl<WarpGemmAttributeMfmaTransposedCDistribution<
         WarpGemmAttributeMfmaImpl_f32_32x32x16_fp8_bf8<WGAttrCtlEnum::Default_>>>;
 
+using WarpGemmMfma_f32_32x32x32_fp8_bf8_CTransposed = WarpGemmImpl<WarpGemmAttributeMfmaIterateK<
+    WarpGemmAttributeMfmaImpl_f32_32x32x16_fp8_bf8<WGAttrCtlEnum::Default_>,
+    2>>;
+
 using WarpGemmMfma_f32_32x32x16_bf8_fp8_CTransposed =
     WarpGemmImpl<WarpGemmAttributeMfmaTransposedCDistribution<
         WarpGemmAttributeMfmaImpl_f32_32x32x16_bf8_fp8<WGAttrCtlEnum::Default_>>>;
 
+using WarpGemmMfma_f32_32x32x32_bf8_fp8_CTransposed = WarpGemmImpl<WarpGemmAttributeMfmaIterateK<
+    WarpGemmAttributeMfmaImpl_f32_32x32x16_bf8_fp8<WGAttrCtlEnum::Default_>,
+    2>>;
+
 using WarpGemmMfma_f32_32x32x16_bf8_bf8_CTransposed =
     WarpGemmImpl<WarpGemmAttributeMfmaTransposedCDistribution<
         WarpGemmAttributeMfmaImpl_f32_32x32x16_bf8_bf8<WGAttrCtlEnum::Default_>>>;
 
+using WarpGemmMfma_f32_32x32x32_bf8_bf8_CTransposed = WarpGemmImpl<WarpGemmAttributeMfmaIterateK<
+    WarpGemmAttributeMfmaImpl_f32_32x32x16_bf8_bf8<WGAttrCtlEnum::Default_>,
+    2>>;
+
 template <index_t swizzle_factor = 2>
 using WarpGemmMfmaFp8Fp8F32M32N32K32SwizzleBTransposedCDistribution =
     WarpGemmImpl<WarpGemmAttributeMfmaIterateKAndTransposedCDistribution_SwizzleB<
diff --git a/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp b/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp
index 9d928a7cfa..f187d6de3c 100644
--- a/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp
@@ -101,19 +101,23 @@ template<> struct Dispatcher<fp8_t, fp8_t, float, 32, 32,  32, false> { using Ty
 template<> struct Dispatcher<fp8_t, fp8_t, float, 16, 16,  32, false> { using Type = WarpGemmMfma_f32_16x16x32_fp8_fp8; };
 template<> struct Dispatcher<fp8_t, fp8_t, float, 16, 16,  64, false> { using Type = WarpGemmMfma_f32_16x16x64_fp8_fp8; };
 template<> struct Dispatcher<fp8_t, fp8_t, float, 32, 32,  16,  true> { using Type = WarpGemmMfma_f32_32x32x16_fp8_fp8_CTransposed; };
+template<> struct Dispatcher<fp8_t, fp8_t, float, 32, 32,  32,  true> { using Type = WarpGemmMfma_f32_32x32x32_fp8_fp8_CTransposed; };
 template<> struct Dispatcher<fp8_t, fp8_t, float, 16, 16,  32,  true> { using Type = WarpGemmMfma_f32_16x16x32_fp8_fp8_CTransposed; };
 template<> struct Dispatcher<fp8_t, bf8_t, float, 32, 32,  16, false> { using Type = WarpGemmMfma_f32_32x32x16_fp8_bf8; };
 template<> struct Dispatcher<fp8_t, bf8_t, float, 32, 32,  16,  true> { using Type = WarpGemmMfma_f32_32x32x16_fp8_bf8_CTransposed; };
+template<> struct Dispatcher<fp8_t, bf8_t, float, 32, 32,  32,  true> { using Type = WarpGemmMfma_f32_32x32x32_fp8_bf8_CTransposed; };
 template<> struct Dispatcher<fp8_t, bf8_t, float, 16, 16,  32, false> { using Type = WarpGemmMfma_f32_16x16x32_fp8_bf8; };
 template<> struct Dispatcher<fp8_t, bf8_t, float, 32, 32,  32, false> { using Type = WarpGemmMfma_f32_32x32x32_fp8_bf8; };
 template<> struct Dispatcher<bf8_t, fp8_t, float, 32, 32,  16, false> { using Type = WarpGemmMfma_f32_32x32x16_bf8_fp8; };
 template<> struct Dispatcher<bf8_t, fp8_t, float, 32, 32,  16,  true> { using Type = WarpGemmMfma_f32_32x32x16_bf8_fp8_CTransposed; };
+template<> struct Dispatcher<bf8_t, fp8_t, float, 32, 32,  32,  true> { using Type = WarpGemmMfma_f32_32x32x16_bf8_fp8_CTransposed; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 32, 32,  16, false> { using Type = WarpGemmMfma_f32_32x32x16_bf8_bf8; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 32, 32,  32, false> { using Type = WarpGemmMfma_f32_32x32x32_bf8_bf8; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 16, 16,  32, false> { using Type = WarpGemmMfma_f32_16x16x32_bf8_bf8; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 16, 16,  32,  true> { using Type = WarpGemmMfma_f32_16x16x32_bf8_bf8_CTransposed; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 16, 16,  64, false> { using Type = WarpGemmMfma_f32_16x16x64_bf8_bf8; };
 template<> struct Dispatcher<bf8_t, bf8_t, float, 32, 32,  16,  true> { using Type = WarpGemmMfma_f32_32x32x16_bf8_bf8_CTransposed; };
+template<> struct Dispatcher<bf8_t, bf8_t, float, 32, 32,  32,  true> { using Type = WarpGemmMfma_f32_32x32x32_bf8_bf8_CTransposed; };
 
 // scale mfma based f8f6f4
 template<WGAttrNumAccessEnum I> struct Dispatcher<fp8_t, fp8_t, float, 16, 16, 128, false, false, false, I> { using Type = WarpGemmMfma_f32_16x16x128_fp8_fp8<I>; };