We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent c9cd497 commit d8ced3aCopy full SHA for d8ced3a
src/vae.hpp
@@ -141,7 +141,7 @@ class AttnBlock : public UnaryBlock {
141
v = ggml_reshape_3d(ctx->ggml_ctx, v, c, h * w, n); // [N, h * w, in_channels]
142
}
143
144
- h_ = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, true, ctx->flash_attn_enabled);
+ h_ = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled);
145
146
if (use_linear) {
147
h_ = proj_out->forward(ctx, h_); // [N, h * w, in_channels]
src/wan.hpp
@@ -572,8 +572,8 @@ namespace WAN {
572
auto v = qkv_vec[2];
573
v = ggml_reshape_3d(ctx->ggml_ctx, v, h * w, c, n); // [t, c, h * w]
574
575
- v = ggml_cont(ctx->ggml_ctx, ggml_ext_torch_permute(ctx->ggml_ctx, v, 1, 0, 2, 3)); // [t, h * w, c]
576
- x = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, true, 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->ggml_ctx, ctx->backend, q, k, v, 1, nullptr, false, ctx->flash_attn_enabled); // [t, h * w, c]
577
578
x = ggml_ext_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3)); // [t, c, h * w]
579
x = ggml_reshape_4d(ctx->ggml_ctx, x, w, h, c, n); // [t, c, h, w]
0 commit comments