DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-12 03:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add linear and attention scale overrides (#1964)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-09-12 01:41:28 +08:00
1 parent 5ebce93342
commit 7f410a3793
39 files changed
+272 -46
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/model/te/llm.hpp
+1 -1
View File
@@ -1359,7 +1359,7 @@ namespace LLM {
x = ggml_ext_cont(ctx->ggml_ctx, kqv);
x = ggml_reshape_3d(ctx->ggml_ctx, x, head_dim * num_heads, n_token, N);
} else {
x = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, num_heads, attention_mask, true, false); // [N, n_token, hidden_size]
x = ggml_ext_attention_ext(ctx, q, k, v, num_heads, attention_mask, true, false); // [N, n_token, hidden_size]
}
x = out_proj->forward(ctx, x); // [N, n_token, hidden_size]