doc

Tencent · Aug 15, 2024 · ba1790d · ba1790d
1 parent 22b3c25
commit ba1790d
Showing 1 changed file with 21 additions and 0 deletions.
diff --git a/docs/developer-guide/operators.md b/docs/developer-guide/operators.md
@@ -71,6 +71,7 @@
 * [Reorg](#reorg)
 * [Requantize](#requantize)
 * [Reshape](#reshape)
+* [RMSNorm](#rmsnorm)
 * [RNN](#rnn)
 * [Scale](#scale)
 * [SELU](#selu)
@@ -1670,6 +1671,26 @@ Reshape flag:
 - -1 = remaining
 - -233 = drop this dim(default)
 
+# RMSNorm
+```
+split x along outmost axis into part x0, x1 ...
+root mean square normalize for each part x0, x1 ...
+y = x * gamma by elementwise
+```
+
+* one_blob_only
+* support_inplace
+
+| param id  | name          | type  | default   | description       |
+| --------- | ------------- | ----- | --------- | ----------------- |
+| 0         | affine_size   | int   | 0         |                   |
+| 1         | eps           | float | 0.001f    | x = x / sqrt(var + eps) |
+| 2         | affine        | int   | 1         |                   |
+
+| weight        | type  | shape                 |
+| ------------- | ----- | --------------------- |
+| gamma_data    | float | [affine_size]         |
+
 # RNN
 Apply a single-layer RNN to a feature sequence of `T` timesteps. The input blob shape is `[w=input_size, h=T]` and the output blob shape is `[w=num_output, h=T]`.