DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf: optimize H3 inference and segmented weight prefetch (#2240)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-30 00:38:14 +08:00
1 parent e7b7ec6d6f
commit 37bc88b5e9
17 files changed
+367 -210
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/device_residency_manager.h
+7 -1
View File
@@ -64,7 +64,13 @@ struct DeviceResidencyManager {
const std::vector<ggml_tensor*>& protected_params) = 0;
virtual WeightPrefetchResult prefetch_params(
uintptr_t owner_id,
const std::vector<ggml_tensor*>& tensors) = 0;
const std::vector<ggml_tensor*>& tensors) = 0;
virtual WeightPrefetchResult prepare_prefetch_params(
uintptr_t owner_id,
const std::vector<ggml_tensor*>& tensors) {
return prefetch_params(owner_id, tensors);
}
virtual void submit_prefetched_params(uintptr_t owner_id) {}
virtual bool activate_prefetched_params(uintptr_t owner_id,
const std::vector<ggml_tensor*>& tensors) = 0;
virtual void clear_prefetched_params(uintptr_t owner_id) = 0;