nncase

A neural network compiler for AI accelerators

These details have not been verified by PyPI

Project links

homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Project description

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

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

These details have not been verified by PyPI

Project links

homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

2.8.2

Apr 28, 2024

This version

2.8.1

Feb 28, 2024

2.8.0

Jan 25, 2024

2.7.0

Dec 28, 2023

2.6.0

Nov 30, 2023

2.5.1

Oct 31, 2023

2.5.0

Oct 30, 2023

2.4.0

Sep 25, 2023

2.3.0

Aug 28, 2023

2.2.0.20230728

Jul 31, 2023

2.1.1.20230721

Jul 21, 2023

2.1.0.20230703

Jul 3, 2023

2.0.0.20230602

Jun 2, 2023

1.9.0.20230322

Mar 23, 2023

1.8.0.20220929

Sep 30, 2022

1.7.1.20220701

Jul 1, 2022

1.7.0.20220530

Jun 6, 2022

1.6.0.20220505

May 9, 2022

1.5.0.20220331

Apr 1, 2022

1.4.0.20220303

Mar 3, 2022

1.3.0.20220127

Jan 28, 2022

1.1.0.20211203

Dec 3, 2021

1.0.0.20211029

Oct 29, 2021

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-2.8.1-cp310-cp310-win_amd64.whl (19.7 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.10 Windows x86-64

nncase-2.8.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.6 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.10 manylinux: glibc 2.17+ x86-64

nncase-2.8.1-cp310-cp310-macosx_10_15_x86_64.whl (25.4 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.10 macOS 10.15+ x86-64

nncase-2.8.1-cp39-cp39-win_amd64.whl (19.7 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.9 Windows x86-64

nncase-2.8.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.6 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.9 manylinux: glibc 2.17+ x86-64

nncase-2.8.1-cp39-cp39-macosx_10_15_x86_64.whl (25.4 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.9 macOS 10.15+ x86-64

nncase-2.8.1-cp38-cp38-win_amd64.whl (19.7 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.8 Windows x86-64

nncase-2.8.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.6 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.8 manylinux: glibc 2.17+ x86-64

nncase-2.8.1-cp38-cp38-macosx_10_15_x86_64.whl (25.4 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.8 macOS 10.15+ x86-64

nncase-2.8.1-cp37-cp37m-win_amd64.whl (19.7 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.7m Windows x86-64

nncase-2.8.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.6 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.7m manylinux: glibc 2.17+ x86-64

nncase-2.8.1-cp37-cp37m-macosx_10_15_x86_64.whl (25.4 MB view hashes)

Uploaded Feb 28, 2024 CPython 3.7m macOS 10.15+ x86-64

Hashes for nncase-2.8.1-cp310-cp310-win_amd64.whl

Hashes for nncase-2.8.1-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`fb0ac0c45c4522ecd34074f57dacce45babf51e7f394f2abe2e44eeed8005575`
MD5	`9a3fbc79a6a8c7ae89d92d96344016b4`
BLAKE2b-256	`626af808d16ccf8f17f187d20e7204b6e9abba30aa4c0150b34e7edcad8a482c`

Hashes for nncase-2.8.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for nncase-2.8.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`2bd2545eeb30b16e038ac9a24588212dbad04253fa49ca5a5d5745ef4c1fa80e`
MD5	`7ab1adea7629d1566739aea842e8cf75`
BLAKE2b-256	`4ef73ceaeb5fa0d40dcdb16a144273c328ecba5a80764e4be848bf14fe524ee7`

Hashes for nncase-2.8.1-cp310-cp310-macosx_10_15_x86_64.whl

Hashes for nncase-2.8.1-cp310-cp310-macosx_10_15_x86_64.whl
Algorithm	Hash digest
SHA256	`6384d77c584eb9768e54b412b1f0b6792db7313d14ad9fe91c9168a020971827`
MD5	`078ab5811481ac1e34af949cd1bd141e`
BLAKE2b-256	`5000f0ad72f8d223f7c46a28f19255e5fbbdd862b54c4678a93e4302a4881df3`

Hashes for nncase-2.8.1-cp39-cp39-win_amd64.whl

Hashes for nncase-2.8.1-cp39-cp39-win_amd64.whl
Algorithm	Hash digest
SHA256	`3e158026b0108dbb14dea14628e13dbccd9fa06ad1ff3bd50131fdc89492c669`
MD5	`356756f188c8038cf5de3bab4c00da58`
BLAKE2b-256	`7eb0c045c4e9b961540921c54a478dda7150b0fa2c7e394d5753e6c555aa61ca`

Hashes for nncase-2.8.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for nncase-2.8.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`26c42d0b4357c83026151722538aff7d9e3c8da1b4a0f32c696d19303c5b0054`
MD5	`8357cdc87020a69909dfb2e24ec13035`
BLAKE2b-256	`8a582c9a5a2069e1e3afd243f155c50f0222552996d7656bfaa5de0247a5ec04`

Hashes for nncase-2.8.1-cp39-cp39-macosx_10_15_x86_64.whl

Hashes for nncase-2.8.1-cp39-cp39-macosx_10_15_x86_64.whl
Algorithm	Hash digest
SHA256	`a64dc19b596c750999559afe3a58fcbb083c8dd9bcbd2a302b79efdad0ce9975`
MD5	`7323ca3e65f07002261a4181c220efbb`
BLAKE2b-256	`78564a54baab16145d26f6841e58b546090e69ba36e11386eaefcc9f007d436b`

Hashes for nncase-2.8.1-cp38-cp38-win_amd64.whl

Hashes for nncase-2.8.1-cp38-cp38-win_amd64.whl
Algorithm	Hash digest
SHA256	`10dedfd95fd0aca749bf06be11c6317c38d12b8e9a1e721171e297430db0b16c`
MD5	`d8f653413c30ed5291aa18cd299aec2b`
BLAKE2b-256	`2588b5fe9a4973e3e4f9d2908fbba89bd7ab612de9e9e503e449780f82add3a8`

Hashes for nncase-2.8.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for nncase-2.8.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`bdf562155d7737de739c0a38b0327500da4138a2a5b7a7828efc1ea33d77cffa`
MD5	`5600bcd7701b44e098c5e6fd8edbb612`
BLAKE2b-256	`27d15254bd8117df5354672ccd50c6a7a1fa40260de53b130ae7d0c9df958916`

Hashes for nncase-2.8.1-cp38-cp38-macosx_10_15_x86_64.whl

Hashes for nncase-2.8.1-cp38-cp38-macosx_10_15_x86_64.whl
Algorithm	Hash digest
SHA256	`3b5b213b17ebe11491dfd38c3379b38c70a7101468b3af5859286cf562730cfd`
MD5	`e44808474de3c0a388cf7cf9f39a0a94`
BLAKE2b-256	`c69890c348b09f0f26e8bfa7186b2d95daa158a529e0274371be1be0e3fd488d`

Hashes for nncase-2.8.1-cp37-cp37m-win_amd64.whl

Hashes for nncase-2.8.1-cp37-cp37m-win_amd64.whl
Algorithm	Hash digest
SHA256	`3a85bb7952e8d87dde87ee043e2700e9ee849a4a60d0e061d18f086eefcc1bbb`
MD5	`cac8959bb7bf1e3678153753bdb0f346`
BLAKE2b-256	`4fda730c13016f5eb6cf48938c1ee28c8b619e9b1d59fc75c41eefb08abfe468`

Hashes for nncase-2.8.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for nncase-2.8.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`31d21a50fe338e3885d55bdf530f132aa88731cc1a229c01938545b161e75a2d`
MD5	`a8c93679e4a5c1c97737f5bbf75e5b51`
BLAKE2b-256	`2730ec3d82915453f07386e88ce519a4d08d6ddc6abb383318525d442b738182`

Hashes for nncase-2.8.1-cp37-cp37m-macosx_10_15_x86_64.whl

Hashes for nncase-2.8.1-cp37-cp37m-macosx_10_15_x86_64.whl
Algorithm	Hash digest
SHA256	`0b1a19d9674f13834d4b8495260fa37d79397d31f5166362bf93e9e2cb4d7d26`
MD5	`4aee232b8c7dcd562e4e108064c5ba5c`
BLAKE2b-256	`1ee97e9921e2106620d7422edb80f65f85326a5898a244c0a647a708f2b3a278`