leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

v4.0 update. (#2371)

Browse Source
This commit is contained in:
Junkai-Wu
2025-06-06 02:39:20 -04:00
committed by GitHub
parent 2e2af190bd
commit 8bdbfca682
254 changed files with 29751 additions and 1980 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/76_blackwell_conv/76_blackwell_conv_dgrad.cu
+3 -3
View File
@@ -490,7 +490,7 @@ int run(Options &options)
int main(int argc, char const **args) {
// CUTLASS must be compiled with CUDA 12.0 Toolkit to run this example
// CUTLASS must be compiled with CUDA 12.8 Toolkit to run this example
// and must have compute capability at least 90.
if (__CUDACC_VER_MAJOR__ < 12 || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ < 8)) {
std::cerr << "This example requires CUDA 12.8 or newer." << std::endl;
@@ -503,11 +503,11 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDevice(&current_device_id));
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
}
//
// Parse options
//
examples/76_blackwell_conv/76_blackwell_conv_fprop.cu
+3 -3
View File
@@ -490,7 +490,7 @@ int run(Options &options)
int main(int argc, char const **args) {
// CUTLASS must be compiled with CUDA 12.0 Toolkit to run this example
// CUTLASS must be compiled with CUDA 12.8 Toolkit to run this example
// and must have compute capability at least 90.
if (__CUDACC_VER_MAJOR__ < 12 || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ < 8)) {
std::cerr << "This example requires CUDA 12.8 or newer." << std::endl;
@@ -503,11 +503,11 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDevice(&current_device_id));
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
}
//
// Parse options
//
examples/76_blackwell_conv/76_blackwell_conv_wgrad.cu
+1 -1
View File
@@ -499,11 +499,11 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDevice(&current_device_id));
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
//
// Parse options
//