cuda: align snake fusion matcher with the other backends (#25460)

* cuda: fix snake fusion type predicate, a and inv_b are F32

The matcher required a->type == x->type while launch_snake reads both
as const float *, matching the CPU and Metal contract where a and inv_b
stay F32. F16/BF16 chains never fused and fell back to the naive path,
and a hypothetical all F16 chain would have read F16 bits as float.
Aligns the predicate and the comment with ggml-cpu.c

* cuda: reject snake fusion on non-contiguous operands

The kernel reads x[idx] and a[c] / inv_b[c] linearly, so a
non-contiguous view passing the matcher would silently read wrong data.
Mirror the contiguity guard already present in the CPU, Vulkan and
Metal matchers.

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index f6632498c57ed88d2a78f776a1ccd341183c962d..bfe449878ea512779098e0a300ce7d09eec9907e 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -3165,18 +3165,21 @@ static int ggml_cuda_try_fuse(ggml_backend_cuda_context * cuda_ctx, ggml_cgraph
                               (a->ne[2]   == 1 && a->ne[3]   == 1);
         const bool shape_ok = ggml_are_same_shape(a, inv_b) && a->ne[0] == 1 && a->ne[1] == x->ne[1];
 
-        // x must be in the supported whitelist and every operand / intermediate
-        // result must share x's type, since launch_snake casts a / inv_b as
-        // float and templates the kernel on a single T. Mixed precision chains
-        // fall back to the naive path.
+        // x is in the supported whitelist and every chain intermediate shares
+        // x's type. launch_snake reads a and inv_b as const float *, so they
+        // stay F32.
         const ggml_tensor * sin1 = cgraph->nodes[i + 1];
         const bool types_ok = (x->type == GGML_TYPE_F32 || x->type == GGML_TYPE_F16 || x->type == GGML_TYPE_BF16) &&
-                              (a->type    == x->type) && (inv_b->type == x->type) &&
+                              (a->type    == GGML_TYPE_F32) && (inv_b->type == GGML_TYPE_F32) &&
                               (mul0->type == x->type) && (sin1->type  == x->type) &&
                               (sqr->type  == x->type) && (mul1->type  == x->type) &&
                               (add->type  == x->type);
 
-        if (types_ok && shape_ok && dim_ok && x_in_add == x) {
+        // kernel reads x[idx] and a[c] / inv_b[c] linearly, so every operand is contiguous
+        const bool contig_ok = ggml_is_contiguous(x) && ggml_is_contiguous(add) &&
+                               ggml_is_contiguous(a) && ggml_is_contiguous(inv_b);
+
+        if (types_ok && shape_ok && dim_ok && contig_ok && x_in_add == x) {
             ggml_cuda_op_snake_fused(*cuda_ctx, x, a, inv_b, add);
             return 4;
         }