gpu-memory-profiler 0.2.0__tar.gz

gpu_memory_profiler-0.2.0/.editorconfig

@@ -0,0 +1,16 @@
+# EditorConfig helps maintain consistent coding styles
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+indent_style = space
+indent_size = 4
+
+[*.md]
+trim_trailing_whitespace = false
+
+[*.py]
+indent_size = 4 

gpu_memory_profiler-0.2.0/.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203, W503
+exclude = .git,__pycache__,docs,build,dist,venv,.venv,.eggs,*.egg,*.egg-info 

gpu_memory_profiler-0.2.0/.github/workflows/ci.yml

@@ -0,0 +1,263 @@
+name: CI
+
+on:
+    push:
+        branches: [main, develop]
+    pull_request:
+        branches: [main, release/v0.2-readiness]
+    schedule:
+        - cron: "0 3 * * *"
+
+jobs:
+    test:
+        if: github.event_name != 'schedule'
+        runs-on: ubuntu-latest
+        strategy:
+            fail-fast: false
+            matrix:
+                python-version: ["3.10", "3.11", "3.12"]
+                framework: [pytorch, tensorflow]
+                exclude:
+                    - python-version: "3.12"
+                      framework: tensorflow
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python ${{ matrix.python-version }}
+              uses: actions/setup-python@v4
+              with:
+                  python-version: ${{ matrix.python-version }}
+
+            - name: Cache pip dependencies
+              uses: actions/cache@v3
+              with:
+                  path: ~/.cache/pip
+                  key: ${{ runner.os }}-pip-${{ matrix.python-version }}-${{ hashFiles('pyproject.toml') }}
+                  restore-keys: |
+                      ${{ runner.os }}-pip-${{ matrix.python-version }}-
+
+            - name: Install base dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install -e . --no-deps
+                  pip install -r requirements-ci-base.txt
+
+            - name: Install framework dependencies
+              run: |
+                  if [ "${{ matrix.framework }}" = "pytorch" ]; then
+                      pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cpu
+                  else
+                      pip install tensorflow-cpu==2.15.0
+                      # Shared tests import gpumemprof modules that require torch at import time.
+                      pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cpu
+                  fi
+
+            - name: Run tests
+              run: |
+                  python3 -m pytest tests/ -v -m "not tui_pilot and not tui_snapshot and not tui_pty" --cov=gpumemprof --cov=tfmemprof --cov-report=xml
+
+            - name: Upload coverage to Codecov
+              uses: codecov/codecov-action@v3
+              with:
+                  file: ./coverage.xml
+                  flags: unittests
+                  name: codecov-umbrella
+
+    tui-pr-gate:
+        if: github.event_name == 'pull_request' || (github.event_name == 'push' && github.ref == 'refs/heads/develop')
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.11"
+
+            - name: Cache pip dependencies
+              uses: actions/cache@v3
+              with:
+                  path: ~/.cache/pip
+                  key: ${{ runner.os }}-pip-tui-pr-${{ hashFiles('pyproject.toml') }}
+                  restore-keys: |
+                      ${{ runner.os }}-pip-tui-pr-
+
+            - name: Install TUI test dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install -e . --no-deps
+                  pip install -r requirements-ci-base.txt
+                  pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cpu
+
+            - name: Run TUI pilot and snapshot suites
+              run: |
+                  python3 -m pytest tests/tui/ -m "tui_pilot or tui_snapshot" -v
+
+    tui-pty-smoke:
+        if: github.event_name == 'schedule' || (github.event_name == 'push' && github.ref == 'refs/heads/main')
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.11"
+
+            - name: Cache pip dependencies
+              uses: actions/cache@v3
+              with:
+                  path: ~/.cache/pip
+                  key: ${{ runner.os }}-pip-tui-pty-${{ hashFiles('pyproject.toml') }}
+                  restore-keys: |
+                      ${{ runner.os }}-pip-tui-pty-
+
+            - name: Install PTY test dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install -e . --no-deps
+                  pip install -r requirements-ci-base.txt
+                  pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cpu
+
+            - name: Run TUI PTY smoke suite
+              run: |
+                  python3 -m pytest tests/e2e/test_tui_pty.py -m tui_pty -v
+
+    lint:
+        if: github.event_name != 'schedule'
+        runs-on: ubuntu-latest
+        strategy:
+            matrix:
+                python-version: ["3.10"]
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python ${{ matrix.python-version }}
+              uses: actions/setup-python@v4
+              with:
+                  python-version: ${{ matrix.python-version }}
+
+            - name: Install dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  # Lint does not require heavy runtime ML dependencies.
+                  pip install -e . --no-deps
+                  pip install black flake8 mypy rich
+
+            - name: Run black
+              run: |
+                  # Temporarily disabled - will be addressed in separate PR
+                  # python3 -m black --check gpumemprof/ tfmemprof/ tests/ examples/
+                  echo "Black formatting check temporarily disabled"
+
+            - name: Run flake8
+              run: |
+                  # Current repository has broad legacy lint debt; keep CI focused on fatal lint errors.
+                  python3 -m flake8 gpumemprof/ tfmemprof/ tests/ examples/ --select=E9,F63,F7,F82 --show-source --statistics
+
+            - name: Run mypy
+              run: |
+                  python3 -m mypy gpumemprof/ tfmemprof/
+
+    docs:
+        if: github.event_name != 'schedule'
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.11"
+
+            - name: Cache pip dependencies
+              uses: actions/cache@v3
+              with:
+                  path: ~/.cache/pip
+                  key: ${{ runner.os }}-pip-docs-${{ hashFiles('pyproject.toml', 'docs/requirements-rtd.txt') }}
+                  restore-keys: |
+                      ${{ runner.os }}-pip-docs-
+
+            - name: Install docs dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install -e . --no-deps
+                  pip install -r docs/requirements-rtd.txt
+
+            - name: Build docs with warnings as errors
+              run: |
+                  python3 -m sphinx -W --keep-going -b html docs docs/_build/html
+
+    build:
+        if: github.event_name != 'schedule'
+        runs-on: ubuntu-latest
+        needs: [test, lint, docs]
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.10"
+
+            - name: Install build dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install build twine
+
+            - name: Build package
+              run: |
+                  python3 -m build
+
+            - name: Check package
+              run: |
+                  twine check dist/*
+
+            - name: Upload build artifacts
+              uses: actions/upload-artifact@v4
+              with:
+                  name: dist
+                  path: dist/
+
+    cli-test:
+        if: github.event_name != 'schedule'
+        runs-on: ubuntu-latest
+        needs: [test, lint, docs]
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.10"
+
+            - name: Install package
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install -e .
+
+            - name: Test CLI tools
+              run: |
+                  gpumemprof --help
+                  tfmemprof --help
+                  gpumemprof info
+                  tfmemprof info
+
+            - name: Run documented CLI examples smoke test
+              env:
+                  CUDA_VISIBLE_DEVICES: ""
+              run: |
+                  python3 -m examples.cli.quickstart
+
+            - name: Run capability matrix smoke test
+              env:
+                  CUDA_VISIBLE_DEVICES: ""
+              run: |
+                  python3 -m examples.cli.capability_matrix --mode smoke --target auto --oom-mode simulated --skip-tui

gpu_memory_profiler-0.2.0/.github/workflows/release.yml

@@ -0,0 +1,36 @@
+name: Release
+
+on:
+    release:
+        types: [published]
+
+jobs:
+    deploy:
+        runs-on: ubuntu-latest
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Set up Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.10"
+
+            - name: Install build dependencies
+              run: |
+                  python3 -m pip install --upgrade pip
+                  pip install build twine
+
+            - name: Build package
+              run: |
+                  python3 -m build
+
+            - name: Check package
+              run: |
+                  twine check dist/*
+
+            - name: Publish to PyPI
+              env:
+                  TWINE_USERNAME: __token__
+                  TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+              run: |
+                  twine upload dist/*

gpu_memory_profiler-0.2.0/.gitignore

@@ -0,0 +1,110 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+debug.log
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+/docs/_build/
+
+# PyBuilder
+.target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# poetry
+poetry.lock
+
+# mypy
+.mypy_cache/
+.dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# VS Code
+.vscode/
+
+# macOS
+.DS_Store
+
+# Virtual environments
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Version files
+gpumemprof/_version.py
+tfmemprof/_version.py
+

gpu_memory_profiler-0.2.0/.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+    - repo: https://github.com/psf/black
+      rev: 24.3.0
+      hooks:
+          - id: black
+    - repo: https://github.com/PyCQA/flake8
+      rev: 7.0.0
+      hooks:
+          - id: flake8
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v4.5.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+          - id: check-added-large-files
+    - repo: https://github.com/pre-commit/mirrors-mypy
+      rev: v1.8.0
+      hooks:
+          - id: mypy

gpu_memory_profiler-0.2.0/.readthedocs.yaml

@@ -0,0 +1,14 @@
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
+sphinx:
+  configuration: docs/conf.py
+  fail_on_warning: true
+
+python:
+  install:
+    - requirements: docs/requirements-rtd.txt

gpu_memory_profiler-0.2.0/CHANGELOG.md

@@ -0,0 +1,188 @@
+# Changelog
+
+All notable changes to GPU Memory Profiler will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.2.0] - Unreleased
+
+### Added
+
+- Launch QA scenario modules under `examples/scenarios/` for CPU telemetry, MPS telemetry, OOM flight recorder coverage, and TensorFlow end-to-end telemetry/diagnose checks.
+- Capability matrix orchestrator (`python -m examples.cli.capability_matrix`) with smoke/full modes, target selection (`auto|cpu|mps|both`), OOM mode controls, and machine-readable reports.
+- Scenario smoke tests (`tests/test_examples_scenarios.py`) and updated TUI pilot coverage for launch quick actions.
+- Updated TUI snapshot baselines for intentional CLI & Actions tab changes.
+
+### Changed
+
+- Drop support for Python 3.8 and 3.9; minimum supported runtime is now Python 3.10.
+- Migration note: users on Python 3.8/3.9 should upgrade to Python 3.10+ or pin `gpu-memory-profiler<0.2.0`.
+- Refresh docs/API examples to match current CLI and profiler behavior.
+- Publish a versioned compatibility matrix for v0.2 and link it from top-level docs.
+- Stabilize benchmark harness defaults (`--iterations 200`) and align benchmark/testing documentation to this baseline.
+- Expand TUI CLI/Playbook guidance and quick actions to highlight diagnose, OOM scenario, and capability matrix workflows.
+- Refresh release-facing docs (`README`, examples guides, `RELEASE_CHECKLIST`, `PROJECT_STATUS`) for v0.2 launch readiness.
+
+### Deprecated
+
+- [Future deprecations will be listed here]
+
+### Removed
+
+- [Future removals will be listed here]
+
+### Fixed
+
+- Remove stale docs references to unsupported CLI options and non-existent profiler APIs.
+- Fix `examples.basic.tensorflow_demo` constructor/API mismatch so the demo runs against the current TensorFlow profiler implementation.
+
+### Security
+
+- [Future security fixes will be listed here]
+
+## [0.1.0] - 2024-12-19
+
+### Added
+
+- **Core PyTorch Profiler (`gpumemprof`)**
+
+  - Real-time GPU memory monitoring with configurable sampling intervals
+  - Memory leak detection using statistical analysis and pattern recognition
+  - Interactive visualizations with matplotlib and plotly support
+  - Context-aware profiling with function decorators and context managers
+  - Command-line interface for standalone usage
+  - Advanced analytics including pattern detection and fragmentation analysis
+  - Alert system with configurable thresholds
+  - Data export capabilities (CSV, JSON)
+  - Automatic memory management with watchdog system
+
+- **Core TensorFlow Profiler (`tfmemprof`)**
+
+  - Real-time TensorFlow GPU memory monitoring
+  - TensorFlow-specific memory leak detection
+  - Integration with TensorFlow's memory management system
+  - Support for TensorFlow sessions and graph execution
+  - Keras model profiling capabilities
+  - Mixed precision profiling support
+  - Multi-GPU strategy profiling
+  - Command-line interface for TensorFlow workflows
+
+- **Visualization & Analysis**
+
+  - Memory timeline plots with interactive features
+  - Function comparison charts
+  - Memory usage heatmaps
+  - Interactive dashboards with Plotly
+  - Memory fragmentation analysis
+  - Performance correlation analysis
+  - Optimization scoring and recommendations
+
+- **Command Line Tools**
+
+  - `gpumemprof` CLI for PyTorch profiling
+  - `tfmemprof` CLI for TensorFlow profiling
+  - System information display
+  - Real-time monitoring capabilities
+  - Background tracking with alerts
+  - Results analysis and visualization
+
+- **CPU Compatibility**
+
+  - CPU memory profiling for systems without GPU
+  - Cross-platform compatibility
+  - CPU-based model training profiling
+  - System RAM monitoring capabilities
+
+- **Testing & Documentation**
+  - Comprehensive test suite for both GPU and CPU environments
+  - PyTorch testing guide with examples
+  - TensorFlow testing guide with examples
+  - CPU compatibility guide
+  - Complete API documentation
+  - Usage examples and tutorials
+  - Troubleshooting guides
+
+### Technical Features
+
+- Modular architecture with 7 core components
+- Thread-safe profiling with background monitoring
+- Configurable sampling intervals and alert thresholds
+- Support for multiple GPU devices
+- Memory snapshot capture and analysis
+- Tensor lifecycle tracking (PyTorch)
+- Graph execution monitoring (TensorFlow)
+- Export capabilities for further analysis
+
+### Documentation
+
+- Comprehensive documentation in `/docs/` directory
+- Quick start guides for both PyTorch and TensorFlow
+- API reference with examples
+- CLI usage guide
+- CPU compatibility guide
+- Testing guides for both frameworks
+- In-depth technical article
+- Contributing guidelines and code of conduct
+
+### Infrastructure
+
+- Open source project structure
+- MIT License
+- Contributing guidelines (CONTRIBUTING.md)
+- Code of Conduct (CODE_OF_CONDUCT.md)
+- Security policy (SECURITY.md)
+- Changelog tracking
+- Development setup instructions
+
+---
+
+## Version History
+
+- **0.1.0** (2024-12-19): Initial release with full PyTorch and TensorFlow support
+
+## Release Notes
+
+### Version 0.1.0
+
+This is the initial release of GPU Memory Profiler, providing comprehensive memory profiling capabilities for both PyTorch and TensorFlow deep learning frameworks. The release includes:
+
+- Complete PyTorch profiler with real-time monitoring, leak detection, and visualization
+- Complete TensorFlow profiler with TensorFlow-specific optimizations
+- Command-line interfaces for both frameworks
+- CPU compatibility for systems without GPU support
+- Comprehensive documentation and testing guides
+- Open source project structure ready for community contributions
+
+### Breaking Changes
+
+None - this is the initial release.
+
+### Known Issues
+
+- Some visualization features may require additional dependencies (PyQt5, tkinter)
+- TensorFlow CLI may have dependency conflicts with certain typing-extensions versions
+- CPU profiling is limited compared to GPU profiling capabilities
+
+### Migration Guide
+
+N/A - this is the initial release.
+
+---
+
+## Contributing to the Changelog
+
+When contributing to the project, please update this changelog by adding entries under the appropriate version section. Follow the format:
+
+- **Added** for new features
+- **Changed** for changes in existing functionality
+- **Deprecated** for soon-to-be removed features
+- **Removed** for now removed features
+- **Fixed** for any bug fixes
+- **Security** for security vulnerability fixes
+
+Use the present tense ("Add" not "Added") and imperative mood ("Move cursor to..." not "Moves cursor to...").
+
+---
+
+**For more information about this project, see the [README](README.md) and [Documentation](docs/index.md).**