From 746cbed20adadcc199e9e1c50173411276e6a360 Mon Sep 17 00:00:00 2001 From: "Piotr Wilkin (ilintar)" Date: Wed, 19 Nov 2025 10:36:33 +0100 Subject: [PATCH] Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition (llama/17332) * Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition * Argh. * Making CISC happy ;) * Integrate CONT tests * Use loopy loop * Skip new tests for (B)F16 for now. --- ggml/src/ggml-cuda/cpy.cu | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-cuda/cpy.cu b/ggml/src/ggml-cuda/cpy.cu index 50612237..c1afde96 100644 --- a/ggml/src/ggml-cuda/cpy.cu +++ b/ggml/src/ggml-cuda/cpy.cu @@ -384,7 +384,8 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg char * src1_ddc = (char *) src1->data; const bool contiguous_srcs = ggml_is_contiguous(src0) && ggml_is_contiguous(src1); - const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) && src0->ne[3] == 1; + const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) && + src0->ne[3] == 1 && nb02 == ne00 * ne01 * (int64_t)ggml_element_size(src0); if (src0->type == src1->type && contiguous_srcs) { GGML_ASSERT(ggml_nbytes(src0) == ggml_nbytes(src1));