From c26fffd88c2b6a0f304e28274ac4a85b96a65933 Mon Sep 17 00:00:00 2001
From: isdanni <leedanni@gmail.com>
Date: Sun, 5 May 2024 20:18:01 -0500
Subject: [PATCH] Specify axis parameter for DequantizeLinear when input rank
 is 1

Signed-off-by: isdanni <leedanni@gmail.com>
---
 docs/Changelog.md              | 4 ++--
 docs/Operators.md              | 2 +-
 onnx/defs/quantization/defs.cc | 5 +++--
 onnx/defs/quantization/old.cc  | 5 ++++-
 4 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/docs/Changelog.md b/docs/Changelog.md
index 8107fbfd86c..6668268839f 100644
--- a/docs/Changelog.md
+++ b/docs/Changelog.md
@@ -22955,7 +22955,7 @@ This version of the operator has been available since version 19 of the default
 
 <dl>
 <dt><tt>axis</tt> : int (default is 1)</dt>
-<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input).</dd>
+<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` where `r = rank(input)`. When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.</dd>
 </dl>
 
 #### Inputs (2 - 3)
@@ -24785,7 +24785,7 @@ This version of the operator has been available since version 21 of the default
 
 <dl>
 <dt><tt>axis</tt> : int (default is 1)</dt>
-<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Used for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` where `r = rank(input)`.</dd>
+<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` where `r = rank(input)`. When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.</dd>
 <dt><tt>block_size</tt> : int (default is 0)</dt>
 <dd>(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given `x` shape `(D0, ..., Di, ..., Dn)`, `y_scale` shape `(S0, ... Si, ...Sn)` and `axis=i`, the accepted range is `[ceil(Di/Si), ceil(Di/(Si-1))-1]`</dd>
 </dl>
diff --git a/docs/Operators.md b/docs/Operators.md
index dab7130c381..246853b82dc 100644
--- a/docs/Operators.md
+++ b/docs/Operators.md
@@ -7374,7 +7374,7 @@ Other versions of this operator: <a href="Changelog.md#DequantizeLinear-10">10</
 
 <dl>
 <dt><tt>axis</tt> : int (default is 1)</dt>
-<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Used for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` where `r = rank(input)`.</dd>
+<dd>(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` where `r = rank(input)`. When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.</dd>
 <dt><tt>block_size</tt> : int (default is 0)</dt>
 <dd>(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given `x` shape `(D0, ..., Di, ..., Dn)`, `y_scale` shape `(S0, ... Si, ...Sn)` and `axis=i`, the accepted range is `[ceil(Di/Si), ceil(Di/(Si-1))-1]`</dd>
 </dl>
diff --git a/onnx/defs/quantization/defs.cc b/onnx/defs/quantization/defs.cc
index 98c1154532d..a68e076b3dd 100644
--- a/onnx/defs/quantization/defs.cc
+++ b/onnx/defs/quantization/defs.cc
@@ -57,9 +57,10 @@ ONNX_OPERATOR_SET_SCHEMA(
         .Output(0, "y", "N-D quantized output tensor. It has same shape as input `x`.", "T2")
         .Attr(
             "axis",
-            "(Optional) The axis of the dequantizing dimension of the input tensor. Used for per-axis and blocked "
+            "(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked "
             "quantization. Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` "
-            "where `r = rank(input)`.",
+            "where `r = rank(input)`. When the rank of the input is 1, per-tensor quantization is applied, "
+            "rendering the axis unnecessary in this scenario.",
             AttributeProto::INT,
             static_cast<int64_t>(1))
         .Attr(
diff --git a/onnx/defs/quantization/old.cc b/onnx/defs/quantization/old.cc
index d2f7cfd8d4a..12be8ad03cb 100644
--- a/onnx/defs/quantization/old.cc
+++ b/onnx/defs/quantization/old.cc
@@ -110,7 +110,10 @@ ONNX_OPERATOR_SET_SCHEMA(
         .Output(0, "y", "N-D full precision output tensor. It has same shape as input 'x'.", "T2")
         .Attr(
             "axis",
-            "(Optional) The axis of the dequantizing dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input).",
+            "(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis quantization. "
+            "Negative value means counting dimensions from the back. Accepted range is `[-r, r-1]` "
+            "where `r = rank(input)`. When the rank of the input is 1, per-tensor quantization is applied, "
+            "rendering the axis unnecessary in this scenario.",
             AttributeProto::INT,
             static_cast<int64_t>(1))
         .TypeConstraint(