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 2, 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:
Newer release available (0.5.3)

Owner

PyPI data
Data sourced directly from PyPI's database.

Credits

Author: rattus

GitHub Statistics

Data verified by PyPI on Sep 2, 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-0.5.0-py3-none-any.whl (24.0 kB view details)

Uploaded Python 3

comfy_aimdo-0.5.0-cp39-abi3-win_arm64.whl (247.7 kB view details)

Uploaded CPython 3.9+Windows ARM64

comfy_aimdo-0.5.0-cp39-abi3-win_amd64.whl (272.9 kB view details)

Uploaded CPython 3.9+Windows x86-64

comfy_aimdo-0.5.0-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (427.0 kB view details)

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

comfy_aimdo-0.5.0-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl (653.4 kB view details)

Uploaded CPython 3.9+manylinux: glibc 2.17+ ARM64

File details

Details for the file comfy_aimdo-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 24.0 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-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9b35da00565db89f6450609202929711e07ed3c6d58e09c8a11fc19e68368f81
MD5 88a09aeae395a4bc838dc6018b0fe15c
BLAKE2b-256 a1b60da4be6d222e2600d7bad8f9d608d480ce28f6ce7bb70c81e05568639a5d

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.0-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-0.5.0-cp39-abi3-win_arm64.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.0-cp39-abi3-win_arm64.whl
  • Upload date:
  • Size: 247.7 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-0.5.0-cp39-abi3-win_arm64.whl
Algorithm Hash digest
SHA256 00cbfbf3429618167c6217c1a83fdff1e89bf6bb32a0efafd2a5451d3997fc76
MD5 1052fd4c797e2708c14002b5b51ff4db
BLAKE2b-256 0e65a67cfee10bd36cdf626d81f059ba51e03690656f00fed1ee7d53aa009087

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.0-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-0.5.0-cp39-abi3-win_amd64.whl.

File metadata

  • Download URL: comfy_aimdo-0.5.0-cp39-abi3-win_amd64.whl
  • Upload date:
  • Size: 272.9 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-0.5.0-cp39-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 cbd19858cd813f8ffbdad8b39f7b21a0089e83f1f5dffb9cbd5e1791acce3af4
MD5 61e4d19aeb98b784f14e49a646716ef1
BLAKE2b-256 263fc143d59d18bfc4a44383791ab4d583c9713bd4340141ece9aeb7fb3e8d12

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.0-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-0.5.0-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.5.0-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Algorithm Hash digest
SHA256 fdb32049a884e0242a6acc243c6b1eec1a3be373e7ebe6efef9a4461d1119598
MD5 5a9d0aa30670f81fe704988f47428829
BLAKE2b-256 17fb17e155279a112e7060bdad741ecc5200476b7a6be0623bf071a7fee43cb1

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.0-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-0.5.0-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl.

File metadata

File hashes

Hashes for comfy_aimdo-0.5.0-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Algorithm Hash digest
SHA256 162fc4d6dbc35a3b889bc5e6f5527fa2bc01fb93d042cb0fb5f07bef17b2757d
MD5 43cfbf2550fd71ca3dfeb35896332c79
BLAKE2b-256 6ba3ea8463a88f8f9cf0edfe87bf2ac2f91bd6aa00912b972aed450b89bad436

See more details on using hashes here.

Provenance

The following attestation bundles were made for comfy_aimdo-0.5.0-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

0.5.3

5 files

0.5.2

5 files

0.5.1

5 files

This release

0.5.0 This release

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