1 files changed, 12 insertions, 0 deletions
diff --git a/ggml.h b/ggml.h
index 68f7833b..f1003984 100644
--- a/ggml.h
+++ b/ggml.h
@@ -343,6 +343,12 @@ extern "C" {
         GGML_TYPE_COUNT,
     };
 
+    // precision
+    enum ggml_prec {
+        GGML_PREC_DEFAULT,
+        GGML_PREC_F32,
+    };
+
     enum ggml_backend_type {
         GGML_BACKEND_CPU = 0,
         GGML_BACKEND_GPU = 10,
@@ -1057,6 +1063,12 @@ extern "C" {
             struct ggml_tensor  * a,
             struct ggml_tensor  * b);
 
+    // change the precision of a matrix multiplication
+    // set to GGML_PREC_F32 for higher precision (useful for phi-2)
+    GGML_API void ggml_mul_mat_set_prec(
+            struct ggml_tensor * a,
+            enum ggml_prec       prec);
+
     // indirect matrix multiplication
     //  ggml_mul_mat_id(ctx, as, ids, id, b) ~= ggml_mul_mat(as[ids[id]], b)
     GGML_API struct ggml_tensor * ggml_mul_mat_id(