From b387ddfd84b4b1f79a6e09910748195e3320e89e Mon Sep 17 00:00:00 2001
From: Eric A Stalee <87948564+Eric-A-Stalee@users.noreply.github.com>
Date: Fri, 28 Aug 2026 12:12:33 -0500
Subject: [PATCH] vulkan: fix missing view-alias dependencies in
 ggml_vk_graph_optimize (#27812)

* vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize

is_src_of doesn't treat two views of one tensor as dependent, so the optimizer reorders nodes across aliased reads and writes.

Result: silently wrong tokens under greedy decoding, different output on every server start, and invalid speculative-decoding acceptance, with nothing logged.

Hits Qwen3.8's recurrent state (and any model with view-aliased state) on AMD and NVIDIA Vulkan.  CUDA is clean.

Compare view_src bases on both sides.

Fixes #27805

* vulkan: don't treat view/no-op nodes as aliasing dependencies

Nodes whose op is NONE, RESHAPE, TRANSPOSE, VIEW or PERMUTE execute nothing, so aliasing through them is not a real dependency. The previous base comparison matched them anyway, which only costs the optimizer reordering freedom.

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* vulkan: make the lambda parameter const and capture is_empty in is_src_of

Code will not compile without these changes.
is_src_of has an empty capture list, so is_empty was not visible inside it, and is_empty took a non-const pointer, while is_src_of receives const ones. Other call sites pass non-const pointers, which still convert as usual.

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
---
 ggml/src/ggml-vulkan/ggml-vulkan.cpp | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 28b2d875d2..320127cdc5 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -17800,20 +17800,32 @@ static void ggml_vk_graph_optimize(ggml_backend_t backend, struct ggml_cgraph *
         return;
     }
 
-    auto const &is_empty = [](ggml_tensor * node) -> bool {
+    auto const &is_empty = [](const ggml_tensor * node) -> bool {
         return node->op == GGML_OP_NONE || node->op == GGML_OP_RESHAPE || node->op == GGML_OP_TRANSPOSE || node->op == GGML_OP_VIEW || node->op == GGML_OP_PERMUTE;
     };
 
-    auto const &is_src_of = [](const ggml_tensor *dst, const ggml_tensor *src) -> bool {
+    auto const &is_src_of = [&is_empty](const ggml_tensor *dst, const ggml_tensor *src) -> bool {
+        auto const &base = [](const ggml_tensor * tensor) {
+            return tensor->view_src ? tensor->view_src : tensor;
+        };
         for (uint32_t s = 0; s < GGML_MAX_SRC; ++s) {
             if (dst->src[s] == src) {
                 return true;
             }
+            if (is_empty(dst) || is_empty(src)) {
+                continue;
+            }
+            // A source view of dst may read storage written through a different view by src.
+            if (dst->src[s] && base(dst->src[s]) == base(src)) {
+                return true;
+            }
+            // Moving dst forward may overwrite storage still read through a view by src.
+            if (src->src[s] && base(dst) == base(src->src[s])) {
+                return true;
+            }
         }
         // implicit dependency if they view the same tensor
-        const ggml_tensor *dst2 = dst->view_src ? dst->view_src : dst;
-        const ggml_tensor *src2 = src->view_src ? src->view_src : src;
-        if (dst2 == src2) {
+        if (base(dst) == base(src)) {
             return true;
         }
         return false;