Add RMS norm and use it (#187)

* add ggml_rms_norm

* update op num

ggml.h

@@ -230,6 +230,7 @@ enum ggml_op {
     GGML_OP_GELU,
     GGML_OP_SILU,
     GGML_OP_NORM, // normalize
+    GGML_OP_RMS_NORM,
 
     GGML_OP_MUL_MAT,
 
@@ -482,6 +483,10 @@ struct ggml_tensor * ggml_norm(
         struct ggml_context * ctx,
         struct ggml_tensor  * a);
 
+struct ggml_tensor * ggml_rms_norm(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * a);
+
 // A: m rows, n columns
 // B: p rows, n columns (i.e. we transpose it internally)
 // result is m columns, p rows