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/vae/auto_encoder_kl.hpp
+1 -1
View File
@@ -142,7 +142,7 @@ public:
v = ggml_reshape_3d(ctx->ggml_ctx, v, c, h * w, n); // [N, h * w, in_channels]
}
h_ = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled);
h_ = ggml_ext_attention_ext(ctx, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled);
if (use_linear) {
h_ = proj_out->forward(ctx, h_); // [N, h * w, in_channels]
src/model/vae/hunyuan_vae.hpp
+1 -1
View File
@@ -193,7 +193,7 @@ namespace Hunyuan {
v = ggml_reshape_3d(ctx->ggml_ctx, v, w * h * t, c, b); // [b, c, t*h*w]
v = ggml_ext_cont(ctx->ggml_ctx, ggml_ext_torch_permute(ctx->ggml_ctx, v, 1, 0, 2, 3)); // [b, t*h*w, c]
x = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled); // [b, t*h*w, c]
x = ggml_ext_attention_ext(ctx, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled); // [b, t*h*w, c]
x = ggml_ext_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3)); // [b, c, t*h*w]
x = ggml_reshape_4d(ctx->ggml_ctx, x, w, h, t, c * b); // [b*c, t, h, w]
src/model/vae/mage_vae.hpp
+1 -1
View File
@@ -253,7 +253,7 @@ namespace MageVAE {
q = to_patches(ctx->ggml_ctx, q);
k = to_patches(ctx->ggml_ctx, k);
v = to_patches(ctx->ggml_ctx, v);
h = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled);
h = ggml_ext_attention_ext(ctx, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled);
h = from_patches(ctx->ggml_ctx, h, np, batch, hp, wp);
if (pad_h > 0) {
h = ggml_ext_slice(ctx->ggml_ctx, h, 1, 0, height);
src/model/vae/minimax_h3_audio_vae.hpp
+1 -2
View File
@@ -174,8 +174,7 @@ namespace MiniMaxH3 {
auto mask = ggml_diag_mask_inf(ctx->ggml_ctx,
ggml_ext_zeros(ctx->ggml_ctx, sequence, sequence, 1, 1),
0);
auto attn_out = ggml_ext_attention_ext(ctx->ggml_ctx,
ctx->backend,
auto attn_out = ggml_ext_attention_ext(ctx,
q,
k,
v,
src/model/vae/minimax_h3_vae.hpp
+1 -2
View File
@@ -291,8 +291,7 @@ namespace MiniMaxH3VAE {
k = ggml_rms_norm(ctx->ggml_ctx, k, 1e-5f);
q = apply_partial_rope(ctx->ggml_ctx, q, pe);
k = apply_partial_rope(ctx->ggml_ctx, k, pe);
auto out = ggml_ext_attention_ext(ctx->ggml_ctx,
ctx->backend,
auto out = ggml_ext_attention_ext(ctx,
q,
k,
v,
src/model/vae/wan_vae.hpp
+2 -2
View File
@@ -615,8 +615,8 @@ namespace WAN {
auto v = qkv_vec[2];
v = ggml_reshape_3d(ctx->ggml_ctx, v, h * w, c, n); // [t, c, h * w]
v = ggml_cont(ctx->ggml_ctx, ggml_ext_torch_permute(ctx->ggml_ctx, v, 1, 0, 2, 3)); // [t, h * w, c]
x = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled); // [t, h * w, c]
v = ggml_cont(ctx->ggml_ctx, ggml_ext_torch_permute(ctx->ggml_ctx, v, 1, 0, 2, 3)); // [t, h * w, c]
x = ggml_ext_attention_ext(ctx, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled); // [t, h * w, c]
x = ggml_ext_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3)); // [t, c, h * w]
x = ggml_reshape_4d(ctx->ggml_ctx, x, w, h, c, n); // [t, c, h, w]