Skip to main content

DXCOM

DXCOM is a compiler SDK by DEEPX that compiles ONNX models into optimized .dxnn binaries for DEEPX NPU (Neural Processing Unit).

It performs hardware-aware quantization, graph optimization, and code generation — all in a single pipeline. The compiled .dxnn file can be deployed and executed on DEEPX NPU via DX-RT (DEEPX Runtime).

Installation

pip install dx-com

Requirements: Python 3.8 – 3.14, Linux (x86_64)

Quick Start

CLI

dxcom -m model.onnx -c config.json -o output/
Argument Description
-m Path to the ONNX model file
-c Path to the JSON configuration file
-o Output directory for compiled artifacts
--opt_level Optimization level: 0 (fast) or 1 (higher accuracy, default)
--gen_log Generate a compilation log
-v Show version

Python API

import dx_com

dx_com.compile(
    model="model.onnx",
    config="config.json",
    output_dir="output/",
    opt_level=1,
)

Parameters

Parameter Type Description
model str Path to the ONNX model file
config str Path to the JSON configuration file
output_dir str Output directory for compiled artifacts
opt_level int Optimization level: 0 (fast) or 1 (higher accuracy). Default: 1
calibration_method str Calibration method. Options: minmax, percentile, mse, entropy
aggressive_partitioning bool Enable aggressive CPU/NPU partitioning. Default: False

Documentation

For detailed technical documentation and user manual, visit DEEPX Developer Portal.

License

This software is the proprietary property of DEEPX Ltd. and is provided exclusively to authorized customers with DEEPX NPU hardware. See LICENSE for details.

Metadata

Release files for dx-com 2.5.0

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 dx-com 2.5.0
File
dx_com-2.5.0-cp314-cp314-manylinux_2_31_x86_64.whl CPython 3.14 CPython 3.14 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp313-cp313-manylinux_2_31_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp312-cp312-manylinux_2_31_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp311-cp311-manylinux_2_31_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp310-cp310-manylinux_2_31_x86_64.whl CPython 3.10 CPython 3.10 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp39-cp39-manylinux_2_31_x86_64.whl CPython 3.9 CPython 3.9 Linux glibc 2.31+ x86-64 Details
dx_com-2.5.0-cp38-cp38-manylinux_2_31_x86_64.whl CPython 3.8 CPython 3.8 Linux glibc 2.31+ x86-64 Details

Total release size: 591.2 MB

Release files / dx_com-2.5.0-cp314-cp314-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp314-cp314-manylinux_2_31_x86_64.whl
Size 85.8 MB
Tags CPython 3.14 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
a8481ea7ba50496e1423b957f87b827b56dfb5df76ca8c6b7ef212773a68806a
BLAKE2b-256 checksum
How to use checksums
1892b42d96545152cf5756b354463c757602e42864bdc849b6499e55a4b3e143
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp313-cp313-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp313-cp313-manylinux_2_31_x86_64.whl
Size 85.8 MB
Tags CPython 3.13 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
a2b7537e058242c3dfbdb0b9362e2d46db01e4a18c23a109d517a2f020e4cf41
BLAKE2b-256 checksum
How to use checksums
3a5e9b82c92182b5514686926100711917eda8b52e68b8eeaafbf736b4c86200
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp312-cp312-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp312-cp312-manylinux_2_31_x86_64.whl
Size 85.7 MB
Tags CPython 3.12 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
43efcb49e1f979bb8d4270fad72a1cab6318f81c0a48578f634640a135555d77
BLAKE2b-256 checksum
How to use checksums
b18622e0d7e7cd8cfea583cc4968592fd93580fbd139e78ed05a2935ef8544a2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp311-cp311-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp311-cp311-manylinux_2_31_x86_64.whl
Size 83.6 MB
Tags CPython 3.11 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
f31b7427ff279e74e9d27820d108bf9eb16f4dc80efae16392405d5af92a4e5d
BLAKE2b-256 checksum
How to use checksums
7ae0ea2dce24360a2604c1ed3e0c56c185b386327f16ff42209ed1b5e68188ab
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp310-cp310-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp310-cp310-manylinux_2_31_x86_64.whl
Size 83.8 MB
Tags CPython 3.10 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
f9ce515434e5b7b33c22717a198ab5d1be641db9d2663d5b5dbb68a1e9a85ab4
BLAKE2b-256 checksum
How to use checksums
e2d9dcf9c80a7abfad78e97cf3c57537e8e0f641768b97982aeb926215bc3a11
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp39-cp39-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp39-cp39-manylinux_2_31_x86_64.whl
Size 83.3 MB
Tags CPython 3.9 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
21f023f74aac0de43e0906ca1ca7a63b3f437285d7ed3bcf986b44f37390e4de
BLAKE2b-256 checksum
How to use checksums
fddbb6e454e2700bb09fef6b12a2996653a6553c530289a117e2a8e1cf3737cc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / dx_com-2.5.0-cp38-cp38-manylinux_2_31_x86_64.whl

Download URL dx_com-2.5.0-cp38-cp38-manylinux_2_31_x86_64.whl
Size 83.1 MB
Tags CPython 3.8 Linux glibc 2.31+ x86-64
SHA-256 checksum
How to use checksums
6499573902d6773df1d1c2d2a6094f34fc3ff63444f7f3261da646204b09de4b
BLAKE2b-256 checksum
How to use checksums
ebe7dff1fa95cdec8fc6a9c1a10e652031a8b391b8d7fbaaa4a4f1771ab70554
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Security for dx-com 2.5.0

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

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.

Release history Release notifications | RSS feed

This release

2.5.0 This release

7 release files No 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