llamafile : disable sgemm for batch-size 1 (ggerganov#9330)

arthw · Nov 18, 2024 · e7f5c7d · e7f5c7d
1 parent 8b7b410
commit e7f5c7d
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;