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
@@ -54,7 +54,7 @@ namespace Hunyuan {
auto k = qkv_vec[1];
auto v = qkv_vec[2];
auto attn_out = ggml_ext_attention_ext(ctx->ggml_ctx, ctx->backend, q, k, v, num_heads, mask, false, ctx->flash_attn_enabled);
auto attn_out = ggml_ext_attention_ext(ctx, q, k, v, num_heads, mask, false, ctx->flash_attn_enabled);
attn_out = self_attn_proj->forward(ctx, attn_out);
// adaLN_modulation