CUDA: use mma PTX instructions for FlashAttention (#11583)

* CUDA: use mma PTX instructions for FlashAttention * __shfl_sync workaround for movmatrix * add __shfl_sync to HIP Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-02-02 19:31:09 +01:00
parent 84ec8a58f7
commit 864a0b67a6
29 changed files with 2058 additions and 998 deletions
--- a/ggml/src/ggml-cuda/mmq.cu
+++ b/ggml/src/ggml-cuda/mmq.cu
@@ -132,7 +132,7 @@ bool ggml_cuda_should_use_mmq(enum ggml_type type, int cc, int64_t ne11) {
        return false;
    }

-    if (int8_mma_available(cc)) {
+    if (new_mma_available(cc)) {
        return true;
    }