AI Model Dynamic Offloader

This project is a pytorch VRAM allocator that implements on-demand offloading of model weights when the primary pytorch VRAM allocator comes under pressure.

Support:

  • Nvidia GPUs only
  • Pytorch 2.8+
  • Cuda 12.8+
  • Windows 11+ / Linux as per python ManyLinux support

How it works:

  • The pytorch application creates a Virtual Base Address Register (VBAR) for a model. Creating a VBAR doesn't cost any VRAM, only GPU virtual address space (which is pretty much free).
  • The pytorch application allocates tensors for model weights within the VBAR. These tensors are initially un-allocated and will segfault if touched.
  • The pytorch application faults in the tensors using the fault() API at the time the tensor is needed. This is where VRAM actually gets allocated.
If the fault() is successful (sufficient VRAM for this tensor):
  1. If the fault() resultant signature is changed or unknown:
    • The application uses tensor::_copy() to populate the weight data on the GPU.
    • The application saves the returned signature against this weight for future comparison
  2. The layer uses the weight tensor.
  3. The application calls unpin() on the tensor to allow it to be freed under pressure later if needed.
If the fault() is unsuccessful (offloaded weight):
  1. The application allocates a temporary regular GPU tensor.
  2. Uses _copy to populate weight data on the GPU.
  3. The layer uses the temporary as the weight.
  4. Pytorch garbage collects the temp when the layer is finished.

see examples/example.py

Priorities:

  • The most recent VBARs are the highest priority and lower addresses in the VBAR take priority over higher addresses.
  • Applications should order their tensor allocations in the VBAR in load-priority order with the lowest addresses for the highest priority weights.
  • Calling fault() on a weight that is higher priority than other weights will cause those lower priority weights to get freed to make space.
  • Having a weight evicted sets that VBAR's watermark to that weight's level. Any weights in the same VBAR above the watermark automatically fail the fault() API. This avoids constantly faulting in all weights each model iteration while allowing the application to just blindly call fault() every layer and check the results. There is no need for the application to manage any VRAM quotas or watermarks.
  • Existing VBARs can be pushed to top priority with the prioritize() API. This allows use of an already loaded or partially model (e.g. using the same model twice in a complex workflow). Using prioritize resets the offload watermark of that model to no offloading, giving its weights priority over any other currently loaded models.

Backend:

  • VBAR allocation is done with cuMemAddressReserve(), faulting with cuMemCreate() and cuMemMap() and all frees done with appropriate converse APIs.
  • For consistency with VBAR memory management, main pytorch allocator plugin is also implemented with cuMemAddressReserve -> cuMemCreate -> cuMemMap. This also behaves a lot better on Windows systems with System Memory fallback.

Caveats:

  • There is no real way for this allocator to tell the difference between high usage and bad fragmentation in the pytorch caching allocator. As we always return success to the pytorch caching allocator it experiences no pressure while weights are being offloaded which means it can run in an extremely fragmented mode. The assumption is model weight access patterns are reasonably regular over blocks or iterations and it finds a good set of sizes to cache. What you should generally do though, is completely flush the pytorch caching allocator before each new model run, which avoids completely un-used reservations from taking priority over the next models weights.

Project links

Data verified by PyPI on Aug 4, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

Owner

PyPI data
Data sourced directly from PyPI's database.

Credits

Author: rattus

GitHub Statistics

Data verified by PyPI on Aug 4, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

Requires

Python >=3.9

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

comfy_aimdo-0.4.13-py3-none-any.whl (22.8 kB view details)

Uploaded Python 3

comfy_aimdo-0.4.13-cp39-abi3-win_arm64.whl (227.5 kB view details)

Uploaded CPython 3.9+Windows ARM64

comfy_aimdo-0.4.13-cp39-abi3-win_amd64.whl (253.7 kB view details)

Uploaded CPython 3.9+Windows x86-64

comfy_aimdo-0.4.13-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl (567.0 kB view details)

Uploaded CPython 3.9+manylinux: glibc 2.17+ ARM64

comfy_aimdo-0.4.13-cp39-abi3-manylinux2010_x86_64.manylinux2014_x86_64.manylinux_2_12_x86_64.manylinux_2_17_x86_64.whl (342.2 kB view details)

Uploaded CPython 3.9+manylinux: glibc 2.12+ x86-64manylinux: glibc 2.17+ x86-64

File details

Details for the file comfy_aimdo-0.4.13-py3-none-any.whl.

File metadata

  • Download URL: comfy_aimdo-0.4.13-py3-none-any.whl
  • Upload date:
  • Size: 22.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for comfy_aimdo-0.4.13-py3-none-any.whl
Algorithm Hash digest
SHA256 92201263e58ffa1ceede2b1f4668abd0874d1cb2e4b1476ca8a0ff6971f88b8a
MD5 fbe2611dcda2e5ec9278a247c0b1911c
BLAKE2b-256 22682e2c45204f7be352b584c26d7d3ec403a1a02c0b663dc97acf51ebef658c

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.4.13-py3-none-any.whl:

Publisher: build-wheels.yml on Comfy-Org/comfy-aimdo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file comfy_aimdo-0.4.13-cp39-abi3-win_arm64.whl.

File metadata

  • Download URL: comfy_aimdo-0.4.13-cp39-abi3-win_arm64.whl
  • Upload date:
  • Size: 227.5 kB
  • Tags: CPython 3.9+, Windows ARM64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for comfy_aimdo-0.4.13-cp39-abi3-win_arm64.whl
Algorithm Hash digest
SHA256 77a694771dfd93a924ca602b3bda7b3fe8c4d04ed05ee7511fa107363da413c3
MD5 3dfb469a9225ecd0ac0344d048b84b87
BLAKE2b-256 7e11b5ca685200a3b1f5c5bea559f0e43bc113f987cc8b24fff15d15b53e8ec3

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.4.13-cp39-abi3-win_arm64.whl:

Publisher: build-wheels.yml on Comfy-Org/comfy-aimdo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file comfy_aimdo-0.4.13-cp39-abi3-win_amd64.whl.

File metadata

  • Download URL: comfy_aimdo-0.4.13-cp39-abi3-win_amd64.whl
  • Upload date:
  • Size: 253.7 kB
  • Tags: CPython 3.9+, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for comfy_aimdo-0.4.13-cp39-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 f677d0b4112a44eaab8fcf46c0c36b6fc9d90feae453fb9c98382ee159f96406
MD5 258b06ea5b97456a43cf9e0dbdc16824
BLAKE2b-256 cefa3383dfc14824ebe12137335542a70aa0e650a5c9da3727aa634d29a61fe3

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.4.13-cp39-abi3-win_amd64.whl:

Publisher: build-wheels.yml on Comfy-Org/comfy-aimdo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file comfy_aimdo-0.4.13-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.4.13-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Algorithm Hash digest
SHA256 dca724ec995eef04faa673be192738830046b435c2c604756e2bbbccb1bc254c
MD5 db1e5cbf80cb70e19f7fea09846a1412
BLAKE2b-256 8a0c31eb7b611e462910a530112aaa7d1485b8c03abdd2c82077237b1d503745

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.4.13-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl:

Publisher: build-wheels.yml on Comfy-Org/comfy-aimdo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file comfy_aimdo-0.4.13-cp39-abi3-manylinux2010_x86_64.manylinux2014_x86_64.manylinux_2_12_x86_64.manylinux_2_17_x86_64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.4.13-cp39-abi3-manylinux2010_x86_64.manylinux2014_x86_64.manylinux_2_12_x86_64.manylinux_2_17_x86_64.whl
Algorithm Hash digest
SHA256 918f55a902fb1bdd840b48a9da339966ab9c45b2eaecad95999167c46e1f6f20
MD5 150155c18cfed1e0cf8b359da9363999
BLAKE2b-256 a5eaca02387a76cc30fdc0df3e7574199c81f5805b622b835473e76001bae82d

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.4.13-cp39-abi3-manylinux2010_x86_64.manylinux2014_x86_64.manylinux_2_12_x86_64.manylinux_2_17_x86_64.whl:

Publisher: build-wheels.yml on Comfy-Org/comfy-aimdo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.4.13 This release

5 files

0.4.12

5 files

0.4.11

5 files

0.4.10

5 files

0.4.9

5 files

0.4.8

5 files

0.4.7

5 files

0.4.6

5 files

0.4.5

5 files

0.4.4

5 files

0.4.3

5 files

0.4.2

5 files

0.4.1

5 files

0.4.0

5 files

0.3.0

5 files

0.2.14

3 files

0.2.12

3 files

0.2.11

3 files

0.2.10

3 files

0.2.9

3 files

0.2.8

3 files

0.2.7

3 files

0.2.6

3 files

0.2.5

3 files

0.2.4

3 files

0.2.3

3 files

0.2.2

3 files

0.2.1

3 files

0.2.0

3 files

0.1.8

3 files

0.1.7

3 files

0.1.6

3 files

0.1.5

3 files

0.1.4

3 files

0.1.3

3 files

0.1.2

11 files

0.1.1

11 files

0.1.0

11 files

0.0.214

3 files

0.0.213

3 files

0.0.4

11 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page