DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 19:36:33 +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/common/block.hpp
+2 -2
View File
@@ -380,14 +380,14 @@ public:
if (xtra_dim) {
context->ne[0] = 320; // reset dim to orig
}
x = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, n_head, nullptr, false, ctx->flash_attn_enabled); // [N, n_token, inner_dim]
x = ggml_ext_attention_ext(ctx, q, k, v, n_head, nullptr, false, ctx->flash_attn_enabled); // [N, n_token, inner_dim]
if (has_ip && ctx->ip_context != nullptr && ctx->ip_scale != 0.0f) {
auto to_k_ip = std::dynamic_pointer_cast<Linear>(blocks["to_k_ip"]);
auto to_v_ip = std::dynamic_pointer_cast<Linear>(blocks["to_v_ip"]);
auto k_ip = to_k_ip->forward(ctx, ctx->ip_context);
auto v_ip = to_v_ip->forward(ctx, ctx->ip_context);
auto x_ip = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k_ip, v_ip, n_head, nullptr, false, ctx->flash_attn_enabled);
auto x_ip = ggml_ext_attention_ext(ctx, q, k_ip, v_ip, n_head, nullptr, false, ctx->flash_attn_enabled);
x = ggml_add(ctx->ggml_ctx, x, ggml_scale(ctx->ggml_ctx, x_ip, ctx->ip_scale));
}