only enable sgemm for prompt processing

ggerganov · Sep 6, 2024 · 3222aae · 3222aae
1 parent 9bc6db2
commit 3222aae
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/ggml/src/llamafile/sgemm.cpp b/ggml/src/llamafile/sgemm.cpp
@@ -1006,6 +1006,10 @@ bool llamafile_sgemm(int64_t m, int64_t n, int64_t k, const void *A, int64_t lda
     assert(nth > 0);
     assert(ith < nth);
 
+    // only enable sgemm for prompt processing
+    if (n < 2)
+        return false;
+
     if (Ctype != GGML_TYPE_F32)
         return false;