CUTLASS 3.5.1 (#1623)

* CUTLASS 3.5.1 * updates, optimizations, fixes
2024-07-29 08:46:24 -04:00
parent 56b46e2d13
commit be60a0b272
312 changed files with 19793 additions and 6775 deletions
@@ -162,7 +162,7 @@ using ShapeMMAWarp = cutlass::gemm::GemmShape<64, 64, 32>;  // <- warp tile M =
 using ShapeMMAOp = cutlass::gemm::GemmShape<8, 8, 4>;  // <- MMA Op tile M = 8, N = 8, K = 4

 // This code section describes how threadblocks are scheduled on GPU
-using SwizzleThreadBlock = cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle<>;  // <- ??
+using SwizzleThreadBlock = cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle<>;

 // This code section describes ?
 using EpilogueOp = cutlass::epilogue::thread::LinearCombination<