auto-generating sphinx docs

main/_modules/torchao/quantization/quant_api.html

@@ -1266,7 +1266,7 @@ <h1>Source code for torchao.quantization.quant_api</h1><div class="highlight"><p
 <span class="sd">    e.g. fp6_e3_m2, fp6_e2_m3, ...</span>
 <span class="sd">    The packing format and kernels are from the fp6-llm paper: https://arxiv.org/abs/2401.14112</span>
 <span class="sd">    github repo: https://github.com/usyd-fsalab/fp6_llm, now renamed to quant-llm</span>
-<span class="sd">    For more details for packing please see: :class:`~torchao.dtypes.fpx.FpxTensorCoreAQTLayout`</span>
+<span class="sd">    For more details for packing please see: :class:`~torchao.dtypes.fpx.FpxTensorCoreAQTTensorImpl`</span>
 
 <span class="sd">    This is experimental, will be merged with `to_affine_quantized_floatx`</span>
 <span class="sd">    in the future</span>

main/_sources/tutorials/template_tutorial.rst.txt

@@ -66,11 +66,11 @@ Example code (the output below is generated automatically):
 
  .. code-block:: none
 
-    tensor([[0.8493, 0.0526, 0.5841],
-            [0.6383, 0.5932, 0.8083],
-            [0.3087, 0.3515, 0.4735],
-            [0.8996, 0.7762, 0.1826],
-            [0.2607, 0.2312, 0.7631]])
+    tensor([[0.7804, 0.8663, 0.7150],
+            [0.4530, 0.6350, 0.2086],
+            [0.9097, 0.1238, 0.0825],
+            [0.5196, 0.2840, 0.3932],
+            [0.3891, 0.3960, 0.5983]])
 
 
 

main/generated/torchao.dtypes.AffineQuantizedTensor.html

@@ -390,7 +390,7 @@
 <h1>AffineQuantizedTensor<a class="headerlink" href="#affinequantizedtensor" title="Permalink to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchao.dtypes.AffineQuantizedTensor">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchao.dtypes.</span></span><span class="sig-name descname"><span class="pre">AffineQuantizedTensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">layout_tensor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">AQTLayout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">block_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Tuple" title="(in Python v3.13)"><span class="pre">Tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/size.html#torch.Size" title="(in PyTorch v2.4)"><span class="pre">Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.13)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.13)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.13)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.13)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_domain</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">ZeroPointDomain</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">ZeroPointDomain.INT</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/torchao/dtypes/affine_quantized_tensor.html#AffineQuantizedTensor"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchao.dtypes.AffineQuantizedTensor" title="Permalink to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchao.dtypes.</span></span><span class="sig-name descname"><span class="pre">AffineQuantizedTensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor_impl</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">AQTTensorImpl</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">block_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Tuple" title="(in Python v3.13)"><span class="pre">Tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/size.html#torch.Size" title="(in PyTorch v2.4)"><span class="pre">Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.13)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.13)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.13)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.13)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_domain</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">ZeroPointDomain</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">ZeroPointDomain.INT</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/torchao/dtypes/affine_quantized_tensor.html#AffineQuantizedTensor"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchao.dtypes.AffineQuantizedTensor" title="Permalink to this definition">¶</a></dt>
 <dd><dl class="simple">
 <dt>Affine quantized tensor subclass. Affine quantization means we quantize the floating point tensor with an affine transformation:</dt><dd><p>quantized_tensor = float_tensor / scale + zero_point</p>
 </dd>
@@ -402,7 +402,7 @@ <h1>AffineQuantizedTensor<a class="headerlink" href="#affinequantizedtensor" tit
 regardless of the internal representation’s type or orientation.</p>
 <dl>
 <dt>fields:</dt><dd><dl class="simple">
-<dt>layout_tensor (AQTLayout): tensor that serves as a general layout storage for the quantized data,</dt><dd><p>e.g. storing plain tensors (int_data, scale, zero_point) or packed formats depending on device
+<dt>tensor_impl (AQTTensorImpl): tensor that serves as a general tensor impl storage for the quantized data,</dt><dd><p>e.g. storing plain tensors (int_data, scale, zero_point) or packed formats depending on device
 and operator/kernel</p>
 </dd>
 <dt>block_size (Tuple[int, …]): granularity of quantization, this means the size of the tensor elements that’s sharing the same qparam</dt><dd><p>e.g. when size is the same as the input tensor dimension, we are using per tensor quantization</p>

main/tutorials/template_tutorial.html

@@ -413,11 +413,11 @@ <h2>Steps<a class="headerlink" href="#steps" title="Permalink to this heading">
 <span class="nb">print</span><span class="p">(</span><a href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="torch.Tensor" class="sphx-glr-backref-module-torch sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>tensor([[0.8493, 0.0526, 0.5841],
-        [0.6383, 0.5932, 0.8083],
-        [0.3087, 0.3515, 0.4735],
-        [0.8996, 0.7762, 0.1826],
-        [0.2607, 0.2312, 0.7631]])
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>tensor([[0.7804, 0.8663, 0.7150],
+        [0.4530, 0.6350, 0.2086],
+        [0.9097, 0.1238, 0.0825],
+        [0.5196, 0.2840, 0.3932],
+        [0.3891, 0.3960, 0.5983]])
 </pre></div>
 </div>
 </section>