feat: add per-module automatic flash attention selection (#2132)

This commit is contained in:
leejet authored and GitHub committed 2026-10-13 22:58:45 +08:00
1 parent 60423ab5f6
commit d763dae3b8
53 files changed
+805 -125

No files matched your search

+1 -1
View File
@@ -761,7 +761,7 @@ ggml_tensor* ggml_ext_attention_ext(ggml_context* ctx,
}
#endif
if (kqv == nullptr && (flash_attn || sage_attn)) {
if (kqv == nullptr && flash_attn) {
// LOG_VERBOSE("attention_ext L_q:%d L_k:%d n_head:%d C:%d d_head:%d N:%d", L_q, L_k, n_head, C, d_head, N);
bool can_use_flash_attn = true;
if (mask != nullptr) {