diff --git a/dsv4/kernels/attention/fmha_sm100.cuh b/dsv4/kernels/attention/fmha_sm100.cuh
index acfc7a49..0c289c5a 100644
--- a/dsv4/kernels/attention/fmha_sm100.cuh
+++ b/dsv4/kernels/attention/fmha_sm100.cuh
@@ -60,14 +60,16 @@ typedef uint16_t bf16_t;
 #endif
 
 // CUTLASS C++ includes (CUDA device code only)
-#if defined(__CUDA_ARCH__)
-#include <cutlass/cutlass.h>
-#include <cute/arch/mma_sm100_umma.hpp>
-#include <cute/arch/copy_sm100.hpp>
-#include <cute/arch/copy_sm100_tma.hpp>
-#include <cute/arch/tmem_allocator_sm100.hpp>
-#include <cute/arch/cluster_sm100.hpp>
-#endif
+// DISABLED: Transitive includes pull in cuda_bf16.h which has a CUDA 13.2 bug.
+// We write tcgen05 PTX directly via inline asm instead.
+// #if defined(__CUDA_ARCH__)
+// #include <cutlass/cutlass.h>
+// #include <cute/arch/mma_sm100_umma.hpp>
+// #include <cute/arch/copy_sm100.hpp>
+// #include <cute/arch/copy_sm100_tma.hpp>
+// #include <cute/arch/tmem_allocator_sm100.hpp>
+// #include <cute/arch/cluster_sm100.hpp>
+// #endif
 
 namespace dsv4 {
 namespace kernels {