CUDA: Blackwell features for non-native builds (llama/18436)

diff --git a/ggml/src/ggml-cuda/CMakeLists.txt b/ggml/src/ggml-cuda/CMakeLists.txt
index 3b438c30ce64b6928960293d3adc8de3ca981798..73f2910b7c56cf81c43abf7a8653de497e282798 100644 (file)
--- a/ggml/src/ggml-cuda/CMakeLists.txt
+++ b/ggml/src/ggml-cuda/CMakeLists.txt
@@ -35,6 +35,20 @@ if (CUDAToolkit_FOUND)
             if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "11.8")
                 list(APPEND CMAKE_CUDA_ARCHITECTURES 89-real)
             endif()
+
+            if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.8")
+                # The CUDA architecture 120f-virtual would in principle work for Blackwell support
+                #     but the newly added "f" suffix conflicted with a preexising regex for validating CUDA architectures in CMake.
+                # So either a recent CMake version or one with the backported fix is needed.
+                # The following versions should work:
+                #   - CMake >= v3.31.8 && CMake < v4.0.0
+                #   - CMake >= v4.0.2
+                # This is NOT documented in the CMake release notes,
+                #     check Modules/Internal/CMakeCUDAArchitecturesValidate.cmake in the CMake git repository instead.
+                # However, the architectures 120a-real and 121a-real should work with basically any CMake version and
+                #     until the release of e.g. Rubin there is no benefit to shipping virtual architectures for Blackwell.
+                list(APPEND CMAKE_CUDA_ARCHITECTURES 120a-real 121a-real)
+            endif()
         endif()
     endif()
     message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
@@ -62,7 +76,7 @@ if (CUDAToolkit_FOUND)
     else()
         foreach(ARCH ${CMAKE_CUDA_ARCHITECTURES})
             if(ARCH MATCHES "^12[0-9](-real|-virtual)?$")
-                message(FATAL_ERROR "Compute capability ${ARCH} used, use ${ARCH}a or ${ARCH}f for Blackwell specific optimizations")
+                message(FATAL_ERROR "Compute capability ${ARCH} used, use ${ARCH}a or ${ARCH}f for Blackwell-specific optimizations")
             endif()
         endforeach()
     endif()