omnimalloc 0.3.0__tar.gz → 0.5.0__tar.gz

{omnimalloc-0.3.0 → omnimalloc-0.5.0}/.pre-commit-config.yaml

@@ -6,6 +6,8 @@ repos:
     rev: v6.0.0
     hooks:
       - id: trailing-whitespace
+        # matplotlib-generated README figures contain trailing whitespace
+        exclude: '^assets/.*\.svg$'
       - id: end-of-file-fixer
       - id: mixed-line-ending
       - id: check-yaml

omnimalloc-0.5.0/CMakeLists.txt

@@ -0,0 +1,81 @@
+cmake_minimum_required(VERSION 3.18...3.30)
+
+# Version is sourced from setuptools-scm via scikit-build-core (git tags). This
+# fallback only applies for standalone CMake calls, not using the build backend.
+if(NOT DEFINED SKBUILD_PROJECT_VERSION)
+  set(SKBUILD_PROJECT_VERSION "0.0.0")
+endif()
+
+project(
+  OmniMalloc
+  VERSION ${SKBUILD_PROJECT_VERSION}
+  LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD 20)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+
+option(ENABLE_CLANG_TIDY "Run clang-tidy with the compiler" OFF)
+if(ENABLE_CLANG_TIDY)
+  find_program(CLANG_TIDY_PROGRAM NAMES clang-tidy REQUIRED)
+endif()
+
+option(ENABLE_IWYU "Run include-what-you-use with the compiler" OFF)
+if(ENABLE_IWYU)
+  find_program(IWYU_PROGRAM NAMES include-what-you-use iwyu REQUIRED)
+endif()
+
+find_package(Python 3.10 REQUIRED COMPONENTS Interpreter Development.Module)
+
+set(THREADS_PREFER_PTHREAD_FLAG ON)
+find_package(Threads REQUIRED)
+
+execute_process(
+  COMMAND "${Python_EXECUTABLE}" -m nanobind --cmake_dir
+  OUTPUT_STRIP_TRAILING_WHITESPACE
+  OUTPUT_VARIABLE nanobind_ROOT)
+find_package(nanobind CONFIG REQUIRED)
+
+nanobind_add_module(
+  _cpp
+  NB_STATIC
+  NOMINSIZE
+  src/cpp/allocators/best_fit.cpp
+  src/cpp/allocators/first_fit.cpp
+  src/cpp/allocators/greedy.cpp
+  src/cpp/allocators/local_search.cpp
+  src/cpp/allocators/omni.cpp
+  src/cpp/allocators/simulated_annealing.cpp
+  src/cpp/allocators/supermalloc/partition.cpp
+  src/cpp/allocators/tabu_search.cpp
+  src/cpp/allocators/telamalloc.cpp
+  src/cpp/primitives/allocation.cpp
+  src/cpp/primitives/antichain.cpp
+  src/cpp/primitives/closure.cpp
+  src/cpp/primitives/linearize.cpp
+  src/cpp/primitives/placement.cpp
+  src/cpp/bindings.cpp)
+
+target_include_directories(_cpp PRIVATE src/cpp)
+target_link_libraries(_cpp PRIVATE Threads::Threads)
+
+if(ENABLE_CLANG_TIDY)
+  set_target_properties(_cpp PROPERTIES CXX_CLANG_TIDY "${CLANG_TIDY_PROGRAM}")
+endif()
+if(ENABLE_IWYU)
+  set_target_properties(_cpp PROPERTIES CXX_INCLUDE_WHAT_YOU_USE
+                                        "${IWYU_PROGRAM}")
+endif()
+
+nanobind_add_stub(
+  _cpp_stub
+  MODULE
+  _cpp
+  OUTPUT
+  ${CMAKE_CURRENT_SOURCE_DIR}/src/python/omnimalloc/_cpp.pyi
+  PYTHON_PATH
+  $<TARGET_FILE_DIR:_cpp>
+  DEPENDS
+  _cpp)
+
+install(TARGETS _cpp LIBRARY DESTINATION omnimalloc)

{omnimalloc-0.3.0 → omnimalloc-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: omnimalloc
-Version: 0.3.0
+Version: 0.5.0
 Summary: Your one-stop shop for static memory allocation.
 Keywords: memory,allocation,allocator,static-allocation
 Author-Email: Fabian Peddinghaus <fabianpedd@gmail.com>
@@ -234,19 +234,85 @@ Requires-Dist: onnx>=1.19.0; extra == "all"
 Requires-Dist: tqdm>=4.66.0; extra == "all"
 Description-Content-Type: text/markdown
 
-# OmniMalloc
+<h1 align="center">OmniMalloc</h1>
 
-Your one-stop shop for static memory allocation.
+<p align="center">State-of-the-art static memory allocation for neural networks.</p>
+
+<p align="center">
+  <a href="https://github.com/fpedd/omnimalloc/actions/workflows/checks.yml"><img src="https://img.shields.io/github/actions/workflow/status/fpedd/omnimalloc/checks.yml?branch=main&label=checks" alt="Checks"></a>
+  <a href="https://github.com/fpedd/omnimalloc/actions/workflows/build.yml"><img src="https://img.shields.io/github/actions/workflow/status/fpedd/omnimalloc/build.yml?branch=main&label=build" alt="Build"></a>
+  <a href="https://pypi.org/project/omnimalloc/"><img src="https://img.shields.io/pypi/v/omnimalloc" alt="PyPI"></a>
+  <a href="https://pypi.org/project/omnimalloc/"><img src="https://img.shields.io/pypi/pyversions/omnimalloc" alt="Python versions"></a>
+  <a href="https://github.com/fpedd/omnimalloc/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/omnimalloc" alt="License"></a>
+</p>
+
+OmniMalloc is a Python library for static memory allocation: given buffers
+with known sizes and lifetimes, assign offsets so that peak memory is minimized.
+This is the memory-planning step at the heart of ML compilers, embedded
+runtimes, and accelerator toolchains.
+
+It ships a collection of allocators and allocation algorithms behind one API,
+implemented with an efficient C++ backend. This includes SuperMalloc, a new
+allocator that outperforms the best open-source alternatives (see benchmarks
+below). OmniMalloc also provides a rich benchmark harness and visualization
+tools to develop and evaluate new allocation strategies.
 
 ## Installation
 
+Install the latest release from PyPI:
+
 ```bash
 pip install omnimalloc
 ```
 
+Or install the development version directly from GitHub:
+
+```bash
+pip install git+https://github.com/fpedd/omnimalloc.git
+```
+
 ## Usage
 
-Please refer to [examples](examples/), in particular [examples/01_basic.py](examples/01_basic.py).
+```python
+from omnimalloc import Allocation, Pool, run_allocation
+
+pool = Pool(id="pool", allocations=(
+    Allocation(id=0, size=64, start=0, end=10),
+    Allocation(id=1, size=64, start=12, end=20),
+    Allocation(id=2, size=32, start=5, end=15),
+))
+
+pool = run_allocation(pool, allocator="supermalloc_allocator", validate=True)
+
+print(pool.size)                                     # 96
+print([alloc.offset for alloc in pool.allocations])  # [0, 0, 64]
+```
+
+On a real problem, the result looks like this: 308 buffers of an ML workload
+packed with no wasted memory.
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/allocation_dark.svg">
+    <img src="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/allocation_light.svg" alt="A solved allocation problem rendered as offset/time rectangles">
+  </picture>
+</p>
+
+See [examples](examples/) for allocator selection, visualization, custom
+allocation sources, and benchmarking.
+
+## Benchmarks
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/hero_dark.svg">
+    <img src="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/hero_light.svg" alt="Solution quality vs. solve time across allocators">
+  </picture>
+</p>
+
+All figures on this page are generated from a deterministic benchmark run by
+[`scripts/generate_readme_assets.py`](scripts/generate_readme_assets.py).
+Run your own campaigns with the [benchmark harness](examples/05_benchmark.py).
 
 ## Development
 

omnimalloc-0.5.0/README.md

@@ -0,0 +1,102 @@
+<h1 align="center">OmniMalloc</h1>
+
+<p align="center">State-of-the-art static memory allocation for neural networks.</p>
+
+<p align="center">
+  <a href="https://github.com/fpedd/omnimalloc/actions/workflows/checks.yml"><img src="https://img.shields.io/github/actions/workflow/status/fpedd/omnimalloc/checks.yml?branch=main&label=checks" alt="Checks"></a>
+  <a href="https://github.com/fpedd/omnimalloc/actions/workflows/build.yml"><img src="https://img.shields.io/github/actions/workflow/status/fpedd/omnimalloc/build.yml?branch=main&label=build" alt="Build"></a>
+  <a href="https://pypi.org/project/omnimalloc/"><img src="https://img.shields.io/pypi/v/omnimalloc" alt="PyPI"></a>
+  <a href="https://pypi.org/project/omnimalloc/"><img src="https://img.shields.io/pypi/pyversions/omnimalloc" alt="Python versions"></a>
+  <a href="https://github.com/fpedd/omnimalloc/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/omnimalloc" alt="License"></a>
+</p>
+
+OmniMalloc is a Python library for static memory allocation: given buffers
+with known sizes and lifetimes, assign offsets so that peak memory is minimized.
+This is the memory-planning step at the heart of ML compilers, embedded
+runtimes, and accelerator toolchains.
+
+It ships a collection of allocators and allocation algorithms behind one API,
+implemented with an efficient C++ backend. This includes SuperMalloc, a new
+allocator that outperforms the best open-source alternatives (see benchmarks
+below). OmniMalloc also provides a rich benchmark harness and visualization
+tools to develop and evaluate new allocation strategies.
+
+## Installation
+
+Install the latest release from PyPI:
+
+```bash
+pip install omnimalloc
+```
+
+Or install the development version directly from GitHub:
+
+```bash
+pip install git+https://github.com/fpedd/omnimalloc.git
+```
+
+## Usage
+
+```python
+from omnimalloc import Allocation, Pool, run_allocation
+
+pool = Pool(id="pool", allocations=(
+    Allocation(id=0, size=64, start=0, end=10),
+    Allocation(id=1, size=64, start=12, end=20),
+    Allocation(id=2, size=32, start=5, end=15),
+))
+
+pool = run_allocation(pool, allocator="supermalloc_allocator", validate=True)
+
+print(pool.size)                                     # 96
+print([alloc.offset for alloc in pool.allocations])  # [0, 0, 64]
+```
+
+On a real problem, the result looks like this: 308 buffers of an ML workload
+packed with no wasted memory.
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/allocation_dark.svg">
+    <img src="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/allocation_light.svg" alt="A solved allocation problem rendered as offset/time rectangles">
+  </picture>
+</p>
+
+See [examples](examples/) for allocator selection, visualization, custom
+allocation sources, and benchmarking.
+
+## Benchmarks
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/hero_dark.svg">
+    <img src="https://raw.githubusercontent.com/fpedd/omnimalloc/main/assets/hero_light.svg" alt="Solution quality vs. solve time across allocators">
+  </picture>
+</p>
+
+All figures on this page are generated from a deterministic benchmark run by
+[`scripts/generate_readme_assets.py`](scripts/generate_readme_assets.py).
+Run your own campaigns with the [benchmark harness](examples/05_benchmark.py).
+
+## Development
+
+```bash
+# Initial setup
+git clone git@github.com:fpedd/omnimalloc.git
+cd omnimalloc
+uv sync --all-extras --group dev
+
+# Run tests, linting, type checking
+uv run pytest
+uv run ruff check --fix && uv run ruff format && uv run ty check
+
+# Setup pre-commit hooks (run once)
+uv run pre-commit install
+
+# Run pre-commit checks manually
+uv run pre-commit run --all-files
+```
+
+## License
+
+Copyright 2025 Fabian Peddinghaus. Licensed under Apache 2.0 License. See [LICENSE](LICENSE) for details.