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 -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,