Metadata-Version: 2.5
Name: ddo-vmm-allocator
Version: 0.1.0rc2
Summary: DDO CUDA VMM allocator primitives for demand-paged model weights
Author: DDO contributors
License: Apache-2.0
License-File: LICENSE
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Provides-Extra: cuda
Requires-Dist: cuda-python>=13.0; extra == 'cuda'
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == 'dev'
Provides-Extra: torch
Requires-Dist: cuda-python>=13.0; extra == 'torch'
Requires-Dist: torch>=2.8; extra == 'torch'
Description-Content-Type: text/markdown

# DDO VMM allocator
Native CUDA Driver VMM and Python adapters consumed by
[DDO](https://github.com/DEVAIEXP/diffusers-dynamic-offloader).
This repository owns native arenas, source/cache transport, event lifetimes,
pressure/admission, the PyTorch pluggable allocator and accounting. It contains
no model-specific runners or weights.
## Documentation
- [User installation](docs/user/installation.md)
- [Developer architecture and contracts](docs/developer/contracts.md)
- [Maintainer builds](docs/developer/builds.md)
- [Tests and validation](docs/developer/validation.md)
- [Experimental package delivery](docs/developer/releases.md)
- [Agent instructions](AGENTS.md)
## Current scope
Selected Windows, native Linux and WSL workloads passed bounded contracts.
Native VMM remains experimental; arbitrary models/drivers, macOS and driver-loss
recovery are not promised. Stable DDO linear/NVMe paths must remain untouched.
Optional Windows/Linux wheels can embed hash-selected DLL/ELF artifacts; Linux
host-wheel assembly passed CPU validation, not broad ABI/CUDA delivery acceptance.
Editable Python installation does not compile native code.
No binary is built/downloaded during import or inference.
Historical probe scaffolding and investigations are preserved locally in ignored
`.internal/documentation/`; current contracts do not depend on those files.
Model benchmarks belong to [DDO examples](https://github.com/DEVAIEXP/ddo-examples).
## License
Apache-2.0. Preserve existing copyright/license/attribution notices in source and
distribution. Driver/toolkit components retain their own applicable terms.
