DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf: reduce fused compute buffers (#2290)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-08 12:28:44 +08:00
1 parent 9234ad822a
commit 5f8c19f98d
11 files changed
+425 -87
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/core/compute_workspace.cpp
+18 -4
View File
@@ -147,8 +147,8 @@ namespace sd {
append(type);
}
} else {
const auto alignment_offset = reinterpret_cast<uintptr_t>(tensor->data) % ggml_backend_get_alignment(external);
append(alignment_offset);
append(tensor->buffer);
append(tensor->data);
}
const int32_t uses = ggml_graph_use_count(graph, tensor);
append(uses);
@@ -164,7 +164,7 @@ namespace sd {
return {};
}
std::unordered_map<const ggml_tensor*, ggml_tensor*> copies;
std::map<ggml_backend_t, ggml_backend_buffer_t> external_buffers;
std::map<std::pair<ggml_backend_t, const void*>, ggml_backend_buffer_t> external_buffers;
for (auto tensor : tensors) {
auto copy = ggml_dup_tensor(context, tensor);
*copy = *tensor;
@@ -179,7 +179,9 @@ namespace sd {
}
auto external = external_backend(source);
if (external != nullptr && source->view_src == nullptr) {
auto& buffer = external_buffers[external];
// Preserve distinct external allocations so overlap checks do not invent aliases.
const void* storage = source->buffer ? static_cast<const void*>(source->buffer) : source;
auto& buffer = external_buffers[{external, storage}];
if (buffer == nullptr) {
buffer = ggml_backend_alloc_buffer(external, 0);
GGML_ASSERT(buffer != nullptr);
@@ -191,6 +193,18 @@ namespace sd {
copy->extra = nullptr;
}
}
for (const auto& entry : copies) {
const auto* source = entry.first;
if (source->view_src && source->buffer) {
const auto* owner = source->view_src;
while (owner->view_src) {
owner = owner->view_src;
}
if (external_backend(owner) != nullptr) {
entry.second->buffer = copies.at(owner)->buffer;
}
}
}
auto copy_graph = ggml_new_graph_custom(context, graph_size, false);
auto map_tensor = [](const ggml_tensor* tensor, void* user_data) -> ggml_tensor* {
const auto& mapped = *static_cast<const std::unordered_map<const ggml_tensor*, ggml_tensor*>*>(user_data);