quantization: autogenerate quantization backend configs for documenta…

…tion (pytorch#75126)

Summary:
Pull Request resolved: pytorch#75126

Quantization has a high volume of configurations of how to quantize an
op for a reference model representation which is useful for a lowering
step for a backend.  An example of this is

```
 {'dtype_configs': [{'input_dtype': torch.quint8,
										 'output_dtype': torch.quint8}],
	'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>,
	'pattern': <class 'torch.nn.modules.conv.ConvTranspose1d'>},
```

These configs are checked into master, and they are created with Python functions.
Therefore, there is no easy way for the user to see what the configs actually
are without running some Python code.

This PR is one approach to document these configs. Here is what this is doing:
1. during documentation build, write a text file of the configs
2. render that text file on a quantization page, with some additional context

In the future, this could be extended to autogenerate better looking tables
such as: op support per backend and dtype, op support per valid quantization settings per backend,
etc.

Test Plan:
```
cd docs
make html
cd html
python -m http.server 8000
// render http://[::]:8000/quantization-backend-configuration.html
// it renders correctly
```

Reviewed By: ejguan

Differential Revision: D35365461

Pulled By: vkuzo

fbshipit-source-id: d60f776ccb57da9db3d09550e4b27bd5e725635a
(cherry picked from commit 14865c0)

.gitignore

@@ -140,6 +140,7 @@ scripts/release_notes/*.json
 compile_commands.json
 *.egg-info/
 docs/source/scripts/activation_images/
+docs/source/scripts/quantization_backend_configs/
 
 ## General
 

docs/Makefile

@@ -15,6 +15,7 @@ help:
 
 figures:
 	@$(PYCMD) source/scripts/build_activation_images.py
+	@$(PYCMD) source/scripts/build_quantization_configs.py
 
 docset: html
 	doc2dash --name $(SPHINXPROJ) --icon $(SOURCEDIR)/_static/img/pytorch-logo-flame.png --enable-js --online-redirect-url https://pytorch.org/docs/ --force $(BUILDDIR)/html/

docs/source/quantization-backend-configuration.rst

@@ -0,0 +1,20 @@
+Quantization Backend Configuration
+----------------------------------
+
+FX Graph Mode Quantization allows the user to configure various
+quantization behaviors of an op in order to match the expectation
+of their backend.
+
+In the future, this document will contain a detailed spec of
+these configurations.
+
+
+Default values for native configurations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Below is the output of the configuration for quantization of ops
+in fbgemm and qnnpack (PyTorch's default quantized backends).
+
+Results:
+
+.. literalinclude:: scripts/quantization_backend_configs/default_backend_config.txt

docs/source/quantization.rst

@@ -489,6 +489,17 @@ and supported quantized modules and functions.
     torch.ao.ns._numeric_suite
     torch.ao.ns._numeric_suite_fx
 
+Quantization Backend Configuration
+----------------------------------
+
+The :doc:`Quantization Backend Configuration <quantization-backend-configuration>` contains documentation
+on how to configure the quantization workflows for various backends.
+
+.. toctree::
+    :hidden:
+
+    quantization-backend-configuration
+
 Quantized Tensors
 ---------------------------------------
 

docs/source/scripts/build_quantization_configs.py

@@ -0,0 +1,23 @@
+"""
+This script will generate default values of quantization configs.
+These are for use in the documentation.
+"""
+
+from torch.ao.quantization.fx.backend_config import get_native_backend_config_dict
+import os.path
+from pprint import pprint
+
+
+# Create a directory for the images, if it doesn't exist
+QUANTIZATION_BACKEND_CONFIG_IMAGE_PATH = os.path.join(
+    os.path.realpath(os.path.join(__file__, "..")),
+    "quantization_backend_configs"
+)
+
+if not os.path.exists(QUANTIZATION_BACKEND_CONFIG_IMAGE_PATH):
+    os.mkdir(QUANTIZATION_BACKEND_CONFIG_IMAGE_PATH)
+
+output_path = os.path.join(QUANTIZATION_BACKEND_CONFIG_IMAGE_PATH, "default_backend_config.txt")
+
+with open(output_path, "w") as f:
+    pprint(get_native_backend_config_dict(), stream=f)