Skip to main content

edgefirst-tensor

Zero-copy tensor memory for edge AI inference pipelines — DMA-BUF, IOSurface, AHardwareBuffer, OpenGL PBO, POSIX shared memory and heap behind one Python API.

PyPI License

Part of the EdgeFirst HAL

edgefirst-tensor is one of five Python packages built from the EdgeFirst Hardware Abstraction Layer.

The EdgeFirstAI/hal repository is the home for all of them — source, issue tracker, architecture documentation and release notes.

Package Provides
edgefirst-tensor Zero-copy tensor allocation and host/GPU/CUDA mapping (this package)
edgefirst-codec JPEG and PNG decoding directly into pre-allocated tensors
edgefirst-image GPU-accelerated colour conversion, resize, letterbox, tiling and drawing
edgefirst-decoder YOLO and ModelPack output decoding
edgefirst-tracker ByteTrack multi-object tracking

This package is the foundation the other four build on; installing any of them installs this one.

Installation

pip install edgefirst-tensor

Requires Python 3.8 or newer and NumPy. Wheels are published for Linux (x86_64, aarch64), macOS (arm64), and Windows (x86_64).

The _codec, _image, _decoder and _tracker extensions locate libedgefirst_tensor.so via DT_RUNPATH=$ORIGIN/../tensor. That assumes every edgefirst.* package lands in the same site-packages tree, which pip normally guarantees. A split layout (pip install --target, some vendored trees) will fail at import with libedgefirst_tensor.so.0: cannot open shared object file. On Windows the library is edgefirst_tensor.dll in that same edgefirst/tensor/ directory and there is no rpath: each sibling package's __init__.py registers the directory with os.add_dll_directory() before loading its extension, because Python 3.8+ does not consult PATH for extension-module DLLs.

Packages install under the PEP 420 edgefirst.* namespace, so imports are edgefirst.tensor, edgefirst.codec, and so on. No package ships an edgefirst/__init__.py — a single one would shadow the namespace and hide its siblings.

Building from source

edgefirst-tensor carries the shared libedgefirst_tensor the codec, image and decoder wheels link against, so these four are built with the dynamic tensor backend:

make wheel            # or, per package, from its directory:
cd crates/python-tensor && maturin build --release

The crate's .cargo/config.toml selects the dynamic backend; a build from the repository root without --config .cargo/tensor-dynamic.toml fails with a message naming the fix. edgefirst.tensor.__tensor_backend__ reports "dynamic" for every wheel built this way.

Quick start

Allocate an image tensor, fill it through a mapped host view, and read it back as NumPy:

import numpy as np
from edgefirst.tensor import Tensor, PixelFormat

# Allocate once; a real pipeline reuses the tensor every frame.
# mem=None selects the best backend available on the platform.
tensor = Tensor.image(1920, 1080, PixelFormat.Rgb, None, "readwrite")

with tensor.map() as view:
    frame = np.asarray(view)  # shape, dtype and strides all carried
    frame[:] = 128

print(tensor.shape, tensor.format, tensor.dtype)

map() returns a HostView implementing the buffer protocol, so np.asarray wraps the tensor's memory without copying — and because the view publishes shape, dtype and the real row stride, no manual reshape is needed and a pitch-aligned DMA buffer is read correctly rather than sheared. The view is released when the with block exits.

The map also owns its cache-coherency bracket, and access chooses the direction. The default "readwrite" flushes the whole buffer on release; a reader does not need that, and on a non-coherent Arm DMA-BUF backing skipping it is a per-frame saving:

with tensor.map("read") as view:
    frame = np.asarray(view)  # read-only view, not writable

pin_host() is the exception: it is deliberately decoupled from coherency so a pinned address can survive across convert() calls, which is why it pairs with an explicit cpu_access() bracket instead.

Handing memory to an external runtime

pin_host() returns a stable host address that outlives any map guard and carries no borrow of the tensor, so a pinned buffer can be given to an inference runtime (TFLite custom allocations, ONNX Runtime external tensors) while your frame loop keeps writing to it:

pin = tensor.pin_host("readwrite")
print(hex(pin.ptr), pin.len, pin.alignment)

# pin.ptr stays valid for the lifetime of `pin` — across re-maps and across
# ImageProcessor.convert() calls — so an external runtime can hold on to it.
pin.release()

What this package provides

API Purpose
Tensor Allocation, reshape, host mapping, NumPy interchange
Tensor.image() Allocate with image dimensions and a pixel format
Tensor.map() / HostView Buffer-protocol host access, released on scope exit
Tensor.pin_host() / HostPin Stable host address for external runtimes
Tensor.cuda_map() / CudaMap Zero-copy CUDA device pointer for TensorRT (Jetson)
TensorMemory, PixelFormat, Region Backend selection, pixel layout, sub-regions
Quantization, Colorimetry Quantization parameters and colour metadata
is_dma_available() and friends Runtime capability probes
Tracing, build_info() Diagnostics

Interoperability

Each edgefirst-* package is a separate PyO3 extension module, so edgefirst.tensor.Tensor and, say, edgefirst.codec.Tensor are different Python classes even though they wrap the same Rust type — a known PyO3 limitation. A tensor still crosses package boundaries safely, through the __edgefirst_tensor__ capsule protocol every Tensor implements:

# Correct — works regardless of which edgefirst.* package produced obj
if hasattr(obj, "__edgefirst_tensor__"):
    ...

# Wrong — always False for a tensor from a sibling package
if isinstance(obj, edgefirst.image.Tensor):
    ...

edgefirst.tensor.EdgeFirstTensorExportable is a typing.Protocol you can annotate a cross-package parameter with, so a type checker accepts a tensor from any edgefirst.* package. See crates/python-common/INTEROP.md for the full protocol — capsule names, lifetime and ownership rules, and versioning.

Versioning and changelog

All four edgefirst-* packages are versioned and released together with the HAL itself, so a given version number refers to the same source tree in every language. Because of that there is no per-package changelog: release notes for every version live in the single CHANGELOG.md in the hal repository, which follows Keep a Changelog and Semantic Versioning.

License

Apache-2.0

Metadata

Release files for edgefirst-tensor 0.41.0

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

Built distributions (wheels)

Table of built distributions (wheels) for edgefirst-tensor 0.41.0
File Actions
edgefirst_tensor-0.41.0-cp311-abi3-win_amd64.whl CPython 3.11 abi3 Windows x86-64 Details for edgefirst_tensor-0.41.0-cp311-abi3-win_amd64.whl
edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl CPython 3.11 abi3 Linux glibc 2.17+ x86-64 Details for edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl CPython 3.11 abi3 Linux glibc 2.17+ ARM64 Details for edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
edgefirst_tensor-0.41.0-cp311-abi3-macosx_11_0_arm64.whl CPython 3.11 abi3 macOS 11.0+ ARM64 Details for edgefirst_tensor-0.41.0-cp311-abi3-macosx_11_0_arm64.whl
edgefirst_tensor-0.41.0-cp38-abi3-win_amd64.whl CPython 3.8 abi3 Windows x86-64 Details for edgefirst_tensor-0.41.0-cp38-abi3-win_amd64.whl
edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl CPython 3.8 abi3 Linux glibc 2.17+ x86-64 Details for edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl CPython 3.8 abi3 Linux glibc 2.17+ ARM64 Details for edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
edgefirst_tensor-0.41.0-cp38-abi3-macosx_11_0_arm64.whl CPython 3.8 abi3 macOS 11.0+ ARM64 Details for edgefirst_tensor-0.41.0-cp38-abi3-macosx_11_0_arm64.whl

Total release size: 9.0 MB

Release files / edgefirst_tensor-0.41.0-cp311-abi3-win_amd64.whl

Download URL edgefirst_tensor-0.41.0-cp311-abi3-win_amd64.whl
Size 1.1 MB
Tags CPython 3.11 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
d6906c67d554428cf7dd55b338a9f7f05f19f047efecab22b20aae6d5b68759f
BLAKE2b-256 checksum
How to use checksums
3332dae0bd00f8b631637e1b55f8b3f303226908192164f2f2666deb61218d01
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl

Download URL edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Size 1.2 MB
Tags CPython 3.11 Linux glibc 2.17+ x86-64 abi3
SHA-256 checksum
How to use checksums
b1bd956edee9e9b8d73a6e3e2142839530f72301ba145ac6a1cf52828af5448d
BLAKE2b-256 checksum
How to use checksums
2332dabc9229089135e91b2dee2d9110356c1d698eabd9ebce90abc12e49a21c
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl

Download URL edgefirst_tensor-0.41.0-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Size 1.1 MB
Tags CPython 3.11 Linux glibc 2.17+ ARM64 abi3
SHA-256 checksum
How to use checksums
01605b41d8bf2f50f4f209887a8147f7e940c9499fd94714162858427e865117
BLAKE2b-256 checksum
How to use checksums
3b1069b90af319a006b99959fb58dc271d1f3ddb89285c6ee0c92ba0ef775c33
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp311-abi3-macosx_11_0_arm64.whl

Download URL edgefirst_tensor-0.41.0-cp311-abi3-macosx_11_0_arm64.whl
Size 1.2 MB
Tags CPython 3.11 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
34f47ef0e243b079cf9ec1d8b28defe789922dfde4bc167281962f01aebd885c
BLAKE2b-256 checksum
How to use checksums
685a34c8f384046f62b954dfcb7a2c454e0cc2c89dc0a3ba78b1c56a993d1849
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp38-abi3-win_amd64.whl

Download URL edgefirst_tensor-0.41.0-cp38-abi3-win_amd64.whl
Size 1.1 MB
Tags CPython 3.8 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
cc061ed98dd8ff1d92748212452525f685d15694881f73055d84ec29009798a9
BLAKE2b-256 checksum
How to use checksums
80a449faab415a4e752b9fcc2f1e7713af1353f0f85c78b995d2523d0cc669a7
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl

Download URL edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Size 1.2 MB
Tags CPython 3.8 Linux glibc 2.17+ x86-64 abi3
SHA-256 checksum
How to use checksums
53a4fbc11ce363ca8982b8a637174945913e6718a0684f3b6086517f4895d3b3
BLAKE2b-256 checksum
How to use checksums
c52e86da2ef3430cae8f5c1005487f207224e4f542dfea01306fb9ac69e8948f
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl

Download URL edgefirst_tensor-0.41.0-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Size 1.1 MB
Tags CPython 3.8 Linux glibc 2.17+ ARM64 abi3
SHA-256 checksum
How to use checksums
df50fa3edfbbff568046892e6edcd548b154e254f5bcb74bde1df600a9bc6076
BLAKE2b-256 checksum
How to use checksums
c9618cc02645eb85da772cecf93fa2605386997f46da5a9120f58d3a348fe6e8
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 16, 2026.

Transparency log

Release files / edgefirst_tensor-0.41.0-cp38-abi3-macosx_11_0_arm64.whl

Download URL edgefirst_tensor-0.41.0-cp38-abi3-macosx_11_0_arm64.whl
Size 1.2 MB
Tags CPython 3.8 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
4e6a4de3c9485b7312b233f102cf865b92ab6d52411a1aac4a725e54b0ebf682
BLAKE2b-256 checksum
How to use checksums
7469cf76b767ee9a143eaed6f172e64272150ebf86cbdd6e08cf37f1659f21d7
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 16, 2026.

Transparency log

Security for edgefirst-tensor 0.41.0

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 8 files in this release have been uploaded with provenance metadata.

Select from 8 files

Attestation for edgefirst_tensor-0.41.0-cp311-abi3-win_amd64.whl

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 16, 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.

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