Skip to content

LLM inference in C/C++

C++ ggml

vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize (#27812)

Eric A Staleeb387ddfd84b4
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;