diff --git a/3rdparty/cutlass b/3rdparty/cutlass
index f3fde58372d3..d112d30a80a9 160000
--- a/3rdparty/cutlass
+++ b/3rdparty/cutlass
@@ -1 +1 @@
-Subproject commit f3fde58372d33e9a5650ba7b80fc48b3b49d40c8
+Subproject commit d112d30a80a9decf8b0937673fe2ce318f9d9a59
diff --git a/cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt b/cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt
index 3b5410033159..aa3a09ef3c96 100644
--- a/cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt
+++ b/cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt
@@ -65,6 +65,8 @@ function(process_target target_name enable_hopper enable_blackwell)
   if(${enable_hopper} AND "90" IN_LIST CMAKE_CUDA_ARCHITECTURES_ORIG)
     # No kernels should be parsed, unless hopper is specified. This is a build
     # time improvement
+    target_compile_options(${target_name}
+                           PRIVATE "-DCUTLASS_ENABLE_GDC_FOR_SM90=1")
     target_compile_definitions(${target_name} PUBLIC COMPILE_HOPPER_TMA_GEMMS)
     target_compile_definitions(${target_name}
                                PUBLIC COMPILE_HOPPER_TMA_GROUPED_GEMMS)
@@ -77,6 +79,8 @@ function(process_target target_name enable_hopper enable_blackwell)
           OR "121" IN_LIST CMAKE_CUDA_ARCHITECTURES_ORIG
          ))
 
+    target_compile_options(${target_name}
+                           PRIVATE "-DCUTLASS_ENABLE_GDC_FOR_SM100=1")
     # Both 100 and 103 support these kernels
     if("100" IN_LIST CMAKE_CUDA_ARCHITECTURES_ORIG
        OR "103" IN_LIST CMAKE_CUDA_ARCHITECTURES_ORIG)
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
index e9442b9d77af..c286989e4d29 100644
--- a/jenkins/L0_Test.groovy
+++ b/jenkins/L0_Test.groovy
@@ -82,7 +82,7 @@ BUILD_CORES_REQUEST = "8"
 BUILD_CORES_LIMIT = "8"
 BUILD_MEMORY_REQUEST = "48Gi"
 BUILD_MEMORY_LIMIT = "64Gi"
-BUILD_JOBS = "8"
+BUILD_JOBS = "4"
 
 SLURM_CORES_REQUEST = "1"
 SLURM_CORES_LIMIT = "1"