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 (CUDA) and AMD GPUs (ROCm/HIP)
  • PyTorch 2.8+
  • CUDA 12.8+ (Nvidia) / ROCm 7+ (AMD)
  • 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.

On AMD, the equivalent HIP APIs (hipMemAddressReserve -> hipMemCreate -> hipMemMap, and their converse calls) are used throughout via the same flow.

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 Sep 8, 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 Sep 8, 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-0.5.3-py3-none-any.whl (24.7 kB view details)

Uploaded Python 3

comfy_aimdo-0.5.3-cp39-abi3-win_arm64.whl (249.0 kB view details)

Uploaded CPython 3.9+Windows ARM64

comfy_aimdo-0.5.3-cp39-abi3-win_amd64.whl (274.4 kB view details)

Uploaded CPython 3.9+Windows x86-64

comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (431.9 kB view details)

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

comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl (658.9 kB view details)

Uploaded CPython 3.9+manylinux: glibc 2.17+ ARM64

File details

Details for the file comfy_aimdo-0.5.3-py3-none-any.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.3-py3-none-any.whl
  • Upload date:
  • Size: 24.7 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-0.5.3-py3-none-any.whl
Algorithm Hash digest
SHA256 b094014439d41a8705103123c97b4ea2a4f8584fae20cb14b9534b6b82b2e97c
MD5 4abea94296a036342e8db068995ff521
BLAKE2b-256 e4ef9a94b88981e51dea163f2fdf98cd28424276fab6a31dc7e22ce89018778f

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.3-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-0.5.3-cp39-abi3-win_arm64.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.3-cp39-abi3-win_arm64.whl
  • Upload date:
  • Size: 249.0 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-0.5.3-cp39-abi3-win_arm64.whl
Algorithm Hash digest
SHA256 d3cde0be60d7195136e3a9bfa50d2b804885751d32800234ccff63cd4bda3bd3
MD5 532d0967c600888f57b8f58417eef3a5
BLAKE2b-256 a724bc09e4597c388925c6aae8a3f955d6caadabf320698c5919fef89244bb0b

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.3-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-0.5.3-cp39-abi3-win_amd64.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.3-cp39-abi3-win_amd64.whl
  • Upload date:
  • Size: 274.4 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-0.5.3-cp39-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 551f991e6a8a881579906e231e68935fe58c80165eabb4ef7e7e76a4c70bebde
MD5 b9d66cdb31635a588ac1d9c2b9a30ab5
BLAKE2b-256 87c630331f08cd8393c0c0b40d6806b0bd4dede09838a2205ae7d544479bbf7d

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.3-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-0.5.3-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Algorithm Hash digest
SHA256 5ddc7e12a2120d3e75e31f6dff52448dd0bd3058277f10f7932e99c20d17ae7a
MD5 c31ee28a7f25c6021b05d6b52d2ac060
BLAKE2b-256 1abcaa38d79aed78aee21d1186e056f8b8e348c6af78874d6f7ed257a6dddf5d

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_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.

File details

Details for the file comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.5.3-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Algorithm Hash digest
SHA256 d87776cbe59e9bc8ad280a60b108d4bd2ba40af408ba2e5f5c04ad401cf35571
MD5 0e9a4a0c3a2828dda3008e1310a81836
BLAKE2b-256 965af38fd0c29a75daf40e62ee7b78b4889a622f12666e7e87e847eab7b8979f

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.3-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.

Release history Release notifications | RSS feed

This release

0.5.3 This release

5 files

0.5.2

5 files

0.5.1

5 files

0.5.0

5 files

0.4.15

5 files

0.4.14

5 files

0.4.13

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

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page