A neural network compiler for AI accelerators

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for sunnycase from gravatar.com sunnycase Avatar for zhangyang2057 from gravatar.com zhangyang2057

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: Apache Software License ( Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR ...)
  • Author: sunnycase
  • Maintainer: sunnycase
  • Tags kendryte, nn, compiler, k210, k510, k230
  • Requires: Python >=3.7
Classifiers

Project description

nncase

GitHub repository Gitee repository GitHub release

nncase is a neural network compiler for AI accelerators.

nncase 是一个为 AI 加速器设计的神经网络编译器。

技术交流 QQ 群：790699378

Telegram: nncase community

Install from binaries

从二进制安装

Download prebuilt binaries from Release.

下载预编译的二进制文件 Release。

Build from source

从源码编译

Build from source

Supported operators

支持的算子

K210/K510

K230

Resources

资源

K210

Architecture

架构

nncase arch

Features

  • Supports multiple inputs and outputs and multi-branch structure
  • Static memory allocation, no heap memory acquired
  • Operators fusion and optimizations
  • Support float and quantized uint8 inference
  • Support post quantization from float model with calibration dataset
  • Flat model with zero copy loading

功能

  • 支持多输入输出网络，支持多分支结构
  • 静态内存分配，不需要堆内存
  • 算子合并和优化
  • 支持 float 和量化 uint8 推理
  • 支持训练后量化，使用浮点模型和量化校准集
  • 平坦模型，支持零拷贝加载

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for sunnycase from gravatar.com sunnycase Avatar for zhangyang2057 from gravatar.com zhangyang2057

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: Apache Software License ( Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR ...)
  • Author: sunnycase
  • Maintainer: sunnycase
  • Tags kendryte, nn, compiler, k210, k510, k230
  • Requires: Python >=3.7
Classifiers

Release history Release notifications | RSS feed

2.9.0

2.8.3

2.8.2

2.8.1

2.8.0

2.7.0

2.6.0

2.5.1

2.5.0

2.4.0

This version

2.3.0

2.2.0.20230728

2.1.1.20230721

2.1.0.20230703

2.0.0.20230602

1.9.0.20230322

1.8.0.20220929

1.7.1.20220701

1.7.0.20220530

1.6.0.20220505

1.5.0.20220331

1.4.0.20220303

1.3.0.20220127

1.1.0.20211203

1.0.0.20211029

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

nncase-2.3.0-cp310-cp310-win_amd64.whl (19.5 MB view details)

Uploaded CPython 3.10 Windows x86-64

nncase-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.2 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

nncase-2.3.0-cp310-cp310-macosx_10_15_x86_64.whl (25.1 MB view details)

Uploaded CPython 3.10 macOS 10.15+ x86-64

nncase-2.3.0-cp39-cp39-win_amd64.whl (19.5 MB view details)

Uploaded CPython 3.9 Windows x86-64

nncase-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.2 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

nncase-2.3.0-cp39-cp39-macosx_10_15_x86_64.whl (25.1 MB view details)

Uploaded CPython 3.9 macOS 10.15+ x86-64

nncase-2.3.0-cp38-cp38-win_amd64.whl (19.5 MB view details)

Uploaded CPython 3.8 Windows x86-64

nncase-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.2 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

nncase-2.3.0-cp38-cp38-macosx_10_15_x86_64.whl (25.1 MB view details)

Uploaded CPython 3.8 macOS 10.15+ x86-64

nncase-2.3.0-cp37-cp37m-win_amd64.whl (19.5 MB view details)

Uploaded CPython 3.7m Windows x86-64

nncase-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.2 MB view details)

Uploaded CPython 3.7m manylinux: glibc 2.17+ x86-64

nncase-2.3.0-cp37-cp37m-macosx_10_15_x86_64.whl (25.1 MB view details)

Uploaded CPython 3.7m macOS 10.15+ x86-64

File details

Details for the file nncase-2.3.0-cp310-cp310-win_amd64.whl.

File metadata

  • Download URL: nncase-2.3.0-cp310-cp310-win_amd64.whl
  • Upload date:
  • Size: 19.5 MB
  • Tags: CPython 3.10, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.5

File hashes

Hashes for nncase-2.3.0-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 fdad8422a910c0711892e48018e60b2dc05a339a12c7d815491fb06d2d92e04b
MD5 ac7d10548e375ef46e50fbce4e5c7dfc
BLAKE2b-256 e27ec5d2e5affc248989882982791104005599924c9044fb6d2d6aede1a69d3f

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 9b48f6f981be85bd325ee3f10f3458a8153f1922f016413b82501101c2d0bcd2
MD5 42bcf5b5c946077db2feeebfc51f1214
BLAKE2b-256 de55a3749398fa893e9e20f25ff00628d213320b908f2fdbef233125c16dbf05

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp310-cp310-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp310-cp310-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 a627e6948a98f6fb8cb6686482fd8363179a5736cabc0687efaa265e25d8d899
MD5 0d7efa7b868b5e33850eee27686eab3b
BLAKE2b-256 06f6d2f040207962c19eacb1f41255be295e2dd2bc3dfea6952e77f8ccbf5bd3

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp39-cp39-win_amd64.whl.

File metadata

  • Download URL: nncase-2.3.0-cp39-cp39-win_amd64.whl
  • Upload date:
  • Size: 19.5 MB
  • Tags: CPython 3.9, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.5

File hashes

Hashes for nncase-2.3.0-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 c554f973d4e43478cd935f7929c6b49b5020dc28b619f8dcadbec9c22d21475c
MD5 d546fd8b79c1aa0830f16c83c39b0f7b
BLAKE2b-256 a985981bf80588052412f91235019dbe2f928d368bf73b38ebc8b4f95751ea2c

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 3453670261510e36a572b4768f33a2b8d76f6133e80f8d1b22604d7442232d43
MD5 53d3d00cc8e7e9440c27b33a9d40c247
BLAKE2b-256 c1acff6ab1d711ea02c9ace64d461556ffb4a67ab323e497e6b58edbbd15a219

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp39-cp39-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp39-cp39-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 288b56a5ab8ac8312fff106378349a987c84783d79818100c940b7f9dfeb06ee
MD5 a979a8dbf19aeee2d09b466acf9d2b4e
BLAKE2b-256 9833ab8099254dcf3d7fe2822b2f46f3badf4ae0ca8c318c1d6993c81dcda413

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp38-cp38-win_amd64.whl.

File metadata

  • Download URL: nncase-2.3.0-cp38-cp38-win_amd64.whl
  • Upload date:
  • Size: 19.5 MB
  • Tags: CPython 3.8, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.5

File hashes

Hashes for nncase-2.3.0-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 643a2771d3448eb4a75b0f4932445f6bd99f0021e40a209db47cc2b2899c3e9f
MD5 d8f8b4d135da74fd0616c5ab69fb8ffb
BLAKE2b-256 4b20a1075e9ca29b230f0b63130dab5e8ff8dfa091052d90d83201881a0187f4

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 38b181307ed602f75839f465bdc1cb6b6e09d46a9614436fe98f8b2f4e789557
MD5 98223839637339777680b68c3fa615dd
BLAKE2b-256 3a33f2a98d36dadb1987fffc5a5d0cdf06cd275b9d8b17fe3ed742f3552d99bb

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp38-cp38-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp38-cp38-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 ca7a8368445ea6bd5e01e08c62f4a764f2d824a4199263f620ce455508dc44b4
MD5 943e082087f84d39edc26a9eadf3c59d
BLAKE2b-256 1bad55af14dc95a68277691e8198256d02f2a3147250c7ca262a62fb78b75663

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: nncase-2.3.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 19.5 MB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.5

File hashes

Hashes for nncase-2.3.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 47596425d769c30198d718a515e8552397acb4f1e2f7c976519047696c7639b5
MD5 9eea1d5db46cf3e02f6e90c9a692fb72
BLAKE2b-256 54134c0e6507561b9f1f8215db64c4cedb67e353189913bd2c637da2db41d9f7

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 7d1f9f702c57a0fb4aa43af84a6b8b631fbea3bf78c57b70d0cecfc19992914e
MD5 53d2e307313c2d7c9dd03440d88dde02
BLAKE2b-256 ef12525bbedfd5ced7d89532972934976de8898c7cc6084b4b7618dbe80dbf1f

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.3.0-cp37-cp37m-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.3.0-cp37-cp37m-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 fc104a627a668af61ca5f4479b48034c0627c4ed20e5d3ec4a5e12f59807c974
MD5 0b74680b48ebb823eeb7331093c70c70
BLAKE2b-256 3f55c38a9d59662bbce2fb45399a2f96ccc9a09d8fd1ed540ecd514709085aae

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page