Skip to main content

ziptensors

Lossless, compressed containers for tensor files (safetensors, GGUF, ONNX, PyTorch zip and opaque files) with random access at tensor speed. Every restored file is bit-exact and proven by its BLAKE3 hash. This is the Python module of ziptensors; the command line tool and the Rust library live in the same repository.

Install

pip install ziptensors            # the module
pip install "ziptensors[torch]"   # with the PyTorch loader's dependency

Wheels are abi3 for CPython 3.11 and later on Linux (x86_64, aarch64), Windows (x64) and macOS. Other platforms build from the source distribution, which needs a Rust toolchain and a C compiler.

Write

import ziptensors

report = ziptensors.encode_file("model.safetensors", "model.ziptensors")  # one file
print(report.output_len, report.total.stored)

# Several files; a (path, member name) pair names the member, a bare path uses the file name.
inputs = ["unet.safetensors", ("downloads/vae.safetensors", "vae/model.safetensors")]
ziptensors.pack(inputs, "pipeline.ziptensors")

mode is fast, balanced (the default of encode_file) or max (the default of pack). A new file is decoded and compared with its source before it replaces anything at the output path.

Read

import ziptensors

container = ziptensors.Container("model.ziptensors", max_total_decoded=64 << 30)
member = container.member()                      # the only member; or container.member("name")
head = member.read(0, 4096)
for tensor in member.tensors:
    print(tensor.name, tensor.dtype, tensor.shape)
member.restore_file("model.safetensors")         # bit-exact copy of the original

Member.read_at(offset, buffer) and Member.decode_tensor_into(name, buffer) fill any writable buffer (a bytearray, a numpy array) with the GIL released. Member.open() returns a seekable read-only file, for example for torch.load.

Untrusted input: max_total_decoded has no default limit. Set it whenever a container comes from somewhere else. The hashes detect damage; they do not authenticate a file.

PyTorch

import torch
from ziptensors.torch import load_state_dict

state = load_state_dict(container.member(), device="cuda", dtype=torch.float16)

Tensors are decoded in place into new torch tensors; on a CUDA or ROCm device the copy overlaps with decoding through pinned staging buffers. ziptensors.torch.load_into(module, member) fills a module built on the meta device. GGUF block-quantized tensors are refused by default; quantized="raw" or quantized="diffusers" hands them over undecoded.

safetensors API

from ziptensors.safetensors import safe_open

with safe_open("model.ziptensors", framework="pt", device="cpu") as f:
    for key in f.keys():
        tensor = f.get_tensor(key)
    rows = f.get_slice("embed.weight")[0:16]

safe_open reads a safetensors member the way safetensors.safe_open reads a file, with the frameworks pt and np.

License

Licensed under either of Apache License, Version 2.0 or MIT license at your option.

Metadata

Release files for ziptensors 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ziptensors 0.1.0
File Size Uploaded Provenance Actions
ziptensors-0.1.0.tar.gz 422.0 kB With provenance Details for ziptensors-0.1.0.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for ziptensors 0.1.0
File Actions
ziptensors-0.1.0-cp311-abi3-win_amd64.whl CPython 3.11 abi3 Windows x86-64 Details for ziptensors-0.1.0-cp311-abi3-win_amd64.whl
ziptensors-0.1.0-cp311-abi3-manylinux_2_28_x86_64.whl CPython 3.11 abi3 Linux glibc 2.28+ x86-64 Details for ziptensors-0.1.0-cp311-abi3-manylinux_2_28_x86_64.whl
ziptensors-0.1.0-cp311-abi3-manylinux_2_28_aarch64.whl CPython 3.11 abi3 Linux glibc 2.28+ ARM64 Details for ziptensors-0.1.0-cp311-abi3-manylinux_2_28_aarch64.whl
ziptensors-0.1.0-cp311-abi3-macosx_11_0_arm64.whl CPython 3.11 abi3 macOS 11.0+ ARM64 Details for ziptensors-0.1.0-cp311-abi3-macosx_11_0_arm64.whl
ziptensors-0.1.0-cp311-abi3-macosx_10_12_x86_64.whl CPython 3.11 abi3 macOS 10.12+ x86-64 Details for ziptensors-0.1.0-cp311-abi3-macosx_10_12_x86_64.whl

Total release size: 4.6 MB

Release files / ziptensors-0.1.0.tar.gz

Download URL ziptensors-0.1.0.tar.gz
Size 422.0 kB
Tags Source
SHA-256 checksum
How to use checksums
295ddded701962677ef7513b12a8dedc293f078443fa699f0346f4554cdb0cfc
BLAKE2b-256 checksum
How to use checksums
9c907b41c938c2636a212b1bf93395f02ccbc854dd514aaf9fc0f4526ef77094
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Release files / ziptensors-0.1.0-cp311-abi3-win_amd64.whl

Download URL ziptensors-0.1.0-cp311-abi3-win_amd64.whl
Size 680.1 kB
Tags CPython 3.11 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
b0fa56e82b98bcd757cd6548057e39df76b894d02212670e5093e52ba98f818f
BLAKE2b-256 checksum
How to use checksums
c34dce004bedcb0e6d3eff88b032ad84c7ad66ef330cc6cba53d369732c7ae1d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Release files / ziptensors-0.1.0-cp311-abi3-manylinux_2_28_x86_64.whl

Download URL ziptensors-0.1.0-cp311-abi3-manylinux_2_28_x86_64.whl
Size 941.0 kB
Tags CPython 3.11 Linux glibc 2.28+ x86-64 abi3
SHA-256 checksum
How to use checksums
27804e833b275072da5eb850bebeddd7eb2a77d2bea65c9e67d4530085484f2a
BLAKE2b-256 checksum
How to use checksums
268647dfd4a3c3f6a7bcedb575a87b04f3177e11961f1405f7ca568578e4bdcb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Release files / ziptensors-0.1.0-cp311-abi3-manylinux_2_28_aarch64.whl

Download URL ziptensors-0.1.0-cp311-abi3-manylinux_2_28_aarch64.whl
Size 899.7 kB
Tags CPython 3.11 Linux glibc 2.28+ ARM64 abi3
SHA-256 checksum
How to use checksums
8818822c2d8fd4d701a7a443ac114e424a2ba4ef6f53775993926e9261342fe6
BLAKE2b-256 checksum
How to use checksums
ebf38bf126ac263eed8ce0055d74aead175f40a8a99088ddf0bbeacd16e8a6a9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Release files / ziptensors-0.1.0-cp311-abi3-macosx_11_0_arm64.whl

Download URL ziptensors-0.1.0-cp311-abi3-macosx_11_0_arm64.whl
Size 777.0 kB
Tags CPython 3.11 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
623c098a4db3e3d2fac5e86297119eb345d8e664d5de65cb951f9d658f510f46
BLAKE2b-256 checksum
How to use checksums
c733fdac6af5be5d4c11bc95a43cb821909f1913d7b63ea8162019e2357c94d2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Release files / ziptensors-0.1.0-cp311-abi3-macosx_10_12_x86_64.whl

Download URL ziptensors-0.1.0-cp311-abi3-macosx_10_12_x86_64.whl
Size 867.8 kB
Tags CPython 3.11 abi3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
a927f5a8719ff430190726d4f713bce716da73b72f718e5d209a6090b8b9abc3
BLAKE2b-256 checksum
How to use checksums
c3028c72009fdfbec39ae5e152c1c60e8c78f3ad7975a5008c767a8137ffa320
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

Security for ziptensors 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 6 files in this release have been uploaded with provenance metadata.

Select from 6 files

Attestation for ziptensors-0.1.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

6 release files Full provenance

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