thor's __CUDA_ARCH__ is 1010 instead of 1100

Author: yzh119

csrc/xqa/mha.cu

@@ -93,7 +93,7 @@ __constant__ constexpr uint32_t cacheVTileSeqLen = 32;
 constexpr uint32_t preferedKHeadPartBytes = 64;
 __constant__ constexpr uint32_t cacheVTileSeqLen = 32;
 #elif __CUDA_ARCH__ == 800 || __CUDA_ARCH__ == 870 || __CUDA_ARCH__ == 900 || \
-    __CUDA_ARCH__ == 1000 || __CUDA_ARCH__ == 1030 || __CUDA_ARCH__ == 1100
+    __CUDA_ARCH__ == 1000 || __CUDA_ARCH__ == 1030 || __CUDA_ARCH__ == 1010
 constexpr uint32_t preferedKHeadPartBytes = 128;
 __constant__ constexpr uint32_t cacheVTileSeqLen = 64;
 #else

csrc/xqa/utils.cuh

@@ -47,7 +47,7 @@ constexpr uint32_t kMAX_SMEM_SIZE = (99u << 10);
 #elif __CUDA_ARCH__ == 800 || __CUDA_ARCH__ == 870
 constexpr uint32_t kMAX_SMEM_SIZE = (163u << 10);
 #elif __CUDA_ARCH__ == 900 || __CUDA_ARCH__ == 1000 || __CUDA_ARCH__ == 1030 || \
-    __CUDA_ARCH__ == 1100
+    __CUDA_ARCH__ == 1010
 constexpr uint32_t kMAX_SMEM_SIZE = (227u << 10);
 #endif
 #endif