Skip to content

LLM inference in C/C++

C++ ggml

hexagon: allow multistream FA (#30218)

Jhen-Jie Hongfe8841a78ad3
diff --git a/ggml/src/ggml-hexagon/ggml-hexagon.cpp b/ggml/src/ggml-hexagon/ggml-hexagon.cpp
index 605c23c68c..7404dbe058 100644
--- a/ggml/src/ggml-hexagon/ggml-hexagon.cpp
+++ b/ggml/src/ggml-hexagon/ggml-hexagon.cpp
@@ -3665,10 +3665,6 @@ static bool ggml_hexagon_supported_flash_attn_ext(const struct ggml_hexagon_sess
return false;
}
- if (dst->ne[3] != 1) {
- return false;
- }
-
struct htp_fa_kernel_params kparams;
if (!ggml_hexagon_precompute_flash_attn_params(sess, op, &kparams)) {
return false;