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

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

No files matched your search

+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]