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

feat: add configurable attention chunk budget for MiniMax-H3 (#2292)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-08 15:50:25 +08:00
1 parent 7bcd4ce8ce
commit de00bafc3d
7 files changed
+103 -43
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/core/cuda/rope.cu
+1 -1
View File
@@ -277,7 +277,7 @@ namespace SD_CUDA_NAMESPACE {
}
static ggml_status rope_prepare(ggml_backend_t, ggml_tensor* const* nodes, int count, void**, size_t* workspace, void*) {
const auto* dst = nodes[count - 1];
const auto* dst = nodes[count - 1];
// Owning casts are fresh outputs; copies into existing storage retain view_src.
const bool fresh_output = !dst->data && !dst->buffer && !dst->view_src;
*workspace = fresh_output ? 0 : ggml_nbytes(dst);