Files
Model-Optimizer/docs/source/conf.py
T
361f7e391b Merge puzzletron compression algorithm (#1121)
### What does this PR do?

Implement puzzletron compression algorithm based on Puzzle paper
(https://arxiv.org/abs/2411.19146)

<details>
<summary> Th list of reviewed and merged MRs that resulted in the
feature/puzzletron branch</summary>

Merging dkorzekwa/any_model to feature/puzzletron

[Add anymodel directories to feature/puzzletron by danielkorzekwa · Pull
Request #974 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/974)
- merged

[Draft: anymodel activation scoring by danielkorzekwa · Pull Request
#989 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/989)
- merged

[Draft: Merge anymodel pruning by danielkorzekwa · Pull Request #990 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/990/)
- merged

[Draft: Merging anymodel:build_library_and_stats by danielkorzekwa ·
Pull Request #993 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/993)
- merged

[Dkorzekwa/any model calc one block scores by danielkorzekwa · Pull
Request #994 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/994)
- merged

[Draft: merge any_model: mip_and_realize_models by danielkorzekwa · Pull
Request #995 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/995)
- merged

[Dkorzekwa/any model other modeqls by danielkorztiekwa · Pull Request
#1007 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1007/)
- merged

PR to 1007: https://github.com/NVIDIA/Model-Optimizer/pull/1039 - merged

[Dkorzekwa/anymodel gptoss by danielkorzekwa · Pull Request #1020 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1020)
- merged

[Merge any_model tutorial by danielkorzekwa · Pull Request #1035 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1035)
- merged

[Merge mbridge distillation for any_model by danielkorzekwa · Pull
Request #1036 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1036)
- merged

[MR branch for the remaining difference between dkorzekwa/any_model an…
by danielkorzekwa · Pull Request #1047 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1047)
- merged

[Dkorzekwa/decilm hf code cleanup by danielkorzekwa · Pull Request #1071
·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1071)
- merged

[Dkorzekwa/decilm hf code cleanup 2 by danielkorzekwa · Pull Request
#1073 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1073)
- merged

[Dkorzekwa/anymodel subblock stats by danielkorzekwa · Pull Request
#1085 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1085)
- merged

[Dkorzekwa/anymodel subblock stats nodecilm by danielkorzekwa · Pull
Request #1102 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1102)
- merged

[Dkorzekwa/decilm cleanup post subblockstats by danielkorzekwa · Pull
Request #1103 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1103)
- merged

[code clean up by danielkorzekwa · Pull Request #1110 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1110)
- merged

Merging into main:

[Activation hooks redesign (reuse hooks component across both minitron
and puzzletron) by danielkorzekwa · Pull Request #1022 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1022)
- merged

[Dkorzekwa/puzzletron use importance hooks from prune by danielkorzekwa
· Pull Request #1115 ·
NVIDIA/Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/pull/1115)
- merged

</details>

<!-- Details about the change. -->

### Usage

Puzzletron tutorial:

https://github.com/NVIDIA/Model-Optimizer/tree/feature/puzzletron/examples/puzzletron

### Testing
The main e2e test for compressing 9 models with Puzzletron:

https://github.com/NVIDIA/Model-Optimizer/blob/feature/puzzletron/tests/gpu/torch/puzzletron/test_puzzletron.py

2-gpu nightly tests: 

-
https://github.com/NVIDIA/Model-Optimizer/actions/runs/24468209205/job/71501061203
-
https://github.com/NVIDIA/Model-Optimizer/actions/runs/24470214159/job/71508152952

### Before your PR is "*Ready for review*"
- Is this change backward compatible?: ✅
- If you copied code from any other sources or added a new PIP
dependency, did you follow guidance in `CONTRIBUTING.md`: ✅
- Did you write any new necessary tests?: ✅
- Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?:
✅



<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Added Puzzletron: end-to-end heterogeneous pruning & NAS workflow with
AnyModel support, example pipelines, deployment and evaluation
utilities, and tools for converting/pruning and exporting compressed
checkpoints.

* **Documentation**
* Comprehensive Puzzletron tutorials, model-specific guides, evaluator
instructions, example configs, and changelog entry.

* **Chores**
* CI/workflow updates (extras installation, longer GPU test timeout),
pre-commit hook exclusion updated, and CODEOWNERS entries added.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Liana Mikaelyan <lmikaelyan@nvidia.com>
Signed-off-by: Liana Mikaelyan <45925959+LianaMikael@users.noreply.github.com>
Signed-off-by: Daniel Korzekwa <daniel.korzekwa@gmail.com>
Signed-off-by: jrausch <jrausch@nvidia.com>
Signed-off-by: root <root@pool0-00848.cm.cluster>
Co-authored-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
Co-authored-by: Liana Mikaelyan <lmikaelyan@nvidia.com>
Co-authored-by: Liana Mikaelyan <45925959+LianaMikael@users.noreply.github.com>
Co-authored-by: J Rausch <38429553+j-rausch@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-16 00:48:11 +05:30

214 lines
8.0 KiB
Python

# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Conf.py file for Sphinx documentation."""
# Configuration file for the Sphinx documentation builder.
#
# This file only contains a selection of the most common options. For a full
# list see the documentation:
# https://www.sphinx-doc.org/en/master/usage/configuration.html
# -- Path setup --------------------------------------------------------------
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#
# import os
# import sys
# sys.path.insert(0, os.path.abspath('.'))
import contextlib
import os
import sys
import sphinx.application
from docutils import nodes
from docutils.nodes import Element
from sphinx.writers.html5 import HTML5Translator
from modelopt import __version__
sys.path.insert(0, os.path.abspath("../../"))
sys.path.append(os.path.abspath("./_ext"))
# Pre-import modelopt.torch so it is cached in sys.modules before Sphinx applies
# autodoc_mock_imports. Mocking triton/tensorrt_llm at the Sphinx level can break
# transitive imports (transformers, transformer_engine, …) and cause modelopt.torch
# to fail inside autosummary. Importing here — while the real packages are still on
# sys.path — avoids that problem entirely.
with contextlib.suppress(Exception):
import modelopt.torch # noqa: F401
# -- Project information -----------------------------------------------------
project = "Model Optimizer" # pylint: disable=C0103
copyright = "2023-2025, NVIDIA Corporation" # pylint: disable=C0103
author = "NVIDIA Corporation" # pylint: disable=C0103
version = __version__
# -- General configuration ---------------------------------------------------
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
"sphinx.ext.autodoc",
"sphinx.ext.autosummary",
"sphinx.ext.githubpages",
"sphinx.ext.napoleon", # Support for NumPy and Google style docstrings
"sphinxarg.ext", # for command-line help documentation
"sphinx_copybutton", # line numbers getting copied so cannot use `:linenos:`
"sphinx_inline_tabs",
"sphinx_togglebutton",
"sphinxcontrib.autodoc_pydantic",
"modelopt_autodoc_pydantic",
]
# Only show copybutton for python code-blocks
copybutton_selector = ", ".join(
[
"div.highlight-python pre",
"div.highlight-ipython3 pre",
"div.highlight-bash pre",
"div.highlight-shell pre",
]
)
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = []
templates_path = ["_templates"]
# -- Options for HTML output -------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
#
html_theme = "sphinx_rtd_theme"
html_theme_options = {
"style_external_links": True,
}
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ["_static"]
html_title = f"Model Optimizer {version}"
html_css_files = ["custom.css"]
html_permalinks_icon = "#" # default icon not rendering properly
# TODO: left here as reference for future
# You can put all these files in the `_static` folder and then activate them as shown below
# html_favicon = "_static/Nvidia_Symbol.png"
# html_theme_options = {
# "light_logo": "Nvidia_Light.png",
# "dark_logo": "Nvidia_Dark.png",
# }
# Mock imports for autodoc
autodoc_mock_imports = ["mpi4py", "tensorrt_llm", "triton"]
autosummary_generate = True
autosummary_imported_members = False
# Only consider members from __all__ if available
autosummary_ignore_module_all = False
# Disable docstring inheritance
autodoc_inherit_docstrings = False
# show inheritance
autodoc_default_options = {"show-inheritance": True}
# Omit type package prefixes and type annotations as much as possible to reduce verbosity
add_module_names = False
python_use_unqualified_type_names = True
# Automatically extract typehints when specified and place them in
# descriptions of the relevant function/method.
autodoc_typehints = "description"
# Don't show class signature with the class' name.
autodoc_class_signature = "separated"
# Order of autodoc
# NOTE: summary table on the top of each page does not follow this order so we should also set __all__ in sorted order
autodoc_member_order = "alphabetical" # can also use `bysource` or `groupwise` to sort members
# autodoc_pydantic model settings
autodoc_pydantic_model_show_config_summary = False
autodoc_pydantic_model_show_validator_summary = False
autodoc_pydantic_model_show_validator_members = False
autodoc_pydantic_model_show_field_summary = False
autodoc_pydantic_model_show_json = True # we overwrite this to show the schema or default or both
autodoc_pydantic_model_signature_prefix = "ModeloptConfig"
autodoc_pydantic_model_modelopt_show_default_dict = True # show default inside json
autodoc_pydantic_model_modelopt_show_json_schema = False # hide json schema
# autodoc_pydantic field settings
autodoc_pydantic_field_swap_name_and_alias = True
autodoc_pydantic_field_doc_policy = "description"
autodoc_pydantic_field_show_alias = False
autodoc_pydantic_field_list_validators = False
autodoc_pydantic_field_show_default = False
class PatchedHTMLTranslator(HTML5Translator):
"""Open all external links in a new tab. Ref: https://stackoverflow.com/a/61669375 ."""
def visit_reference(self, node: Element) -> None:
"""Visit a reference node."""
atts = {"class": "reference"}
if node.get("internal") or "refuri" not in node:
atts["class"] += " internal"
else:
atts["class"] += " external"
# ---------------------------------------------------------
# Customize behavior (open in new tab, secure linking site)
atts["target"] = "_blank"
atts["rel"] = "noopener noreferrer"
# ---------------------------------------------------------
if "refuri" in node:
atts["href"] = node["refuri"] or "#"
if self.settings.cloak_email_addresses and atts["href"].startswith("mailto:"):
atts["href"] = self.cloak_mailto(atts["href"])
self.in_mailto = True
else:
assert "refid" in node, 'References must have "refuri" or "refid" attribute.'
atts["href"] = "#" + node["refid"]
if not isinstance(node.parent, nodes.TextElement):
assert len(node) == 1 and isinstance(node[0], nodes.image)
atts["class"] += " image-reference"
if "reftitle" in node:
atts["title"] = node["reftitle"]
if "target" in node:
atts["target"] = node["target"]
self.body.append(self.starttag(node, "a", "", **atts))
if node.get("secnumber"):
self.body.append(("%s" + self.secnumber_suffix) % ".".join(map(str, node["secnumber"])))
def setup(app: sphinx.application.Sphinx) -> None:
"""Setup according to the Sphinx extension API."""
app.set_translator("html", PatchedHTMLTranslator)