Skip to main content

A neural network compiler for AI accelerators

Project description

nncase

License compiler-build

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


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


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-2.2.0.20230728-cp310-cp310-win_amd64.whl (19.2 MB view details)

Uploaded CPython 3.10 Windows x86-64

nncase-2.2.0.20230728-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.0 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

nncase-2.2.0.20230728-cp310-cp310-macosx_10_15_x86_64.whl (24.8 MB view details)

Uploaded CPython 3.10 macOS 10.15+ x86-64

nncase-2.2.0.20230728-cp39-cp39-win_amd64.whl (19.2 MB view details)

Uploaded CPython 3.9 Windows x86-64

nncase-2.2.0.20230728-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.0 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

nncase-2.2.0.20230728-cp39-cp39-macosx_10_15_x86_64.whl (24.8 MB view details)

Uploaded CPython 3.9 macOS 10.15+ x86-64

nncase-2.2.0.20230728-cp38-cp38-win_amd64.whl (19.2 MB view details)

Uploaded CPython 3.8 Windows x86-64

nncase-2.2.0.20230728-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.0 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

nncase-2.2.0.20230728-cp38-cp38-macosx_10_15_x86_64.whl (24.8 MB view details)

Uploaded CPython 3.8 macOS 10.15+ x86-64

nncase-2.2.0.20230728-cp37-cp37m-win_amd64.whl (19.2 MB view details)

Uploaded CPython 3.7m Windows x86-64

nncase-2.2.0.20230728-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30.0 MB view details)

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

nncase-2.2.0.20230728-cp37-cp37m-macosx_10_15_x86_64.whl (24.8 MB view details)

Uploaded CPython 3.7m macOS 10.15+ x86-64

File details

Details for the file nncase-2.2.0.20230728-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 289ff9760413df0387f5e3e27b50c7911c043f852173447bf0a001c8ac6ae85d
MD5 24f97dbed3d0b6ebb412577b213276b1
BLAKE2b-256 7d1dafae8bad3564e4d284377ceb2575fbbcac8851da787dc104a5d7a4c2280f

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 7b2bfd069a8cf5585b5293ccc5529052848283e86736eb7426a77d3c1dcfac54
MD5 5f999df368f4888716db58dc6fe87551
BLAKE2b-256 aaa470003d988f6082de1c30f15bdee394cecd80fe15d809d16ad1d1082fb891

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp310-cp310-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp310-cp310-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 e6f97f80421661506e3af8df0c009f7b56fe08a30ab74c07d5cdd51730cef515
MD5 59463572b81d284c4f5095d1cbdc1da8
BLAKE2b-256 2a4c76cb44ef9aa59011615aa8faece9f3abae94b7e29b5935cb9d0f7400c378

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp39-cp39-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 4d9ca5395392a376e3486c58c7986063786af094745621b268b544d20c06964e
MD5 97c03f57f731ea37284394275e8909f2
BLAKE2b-256 0b56b65e2ac335a8821fab8c70dd922a3a5aeac607d77148be5ac8ad6b5d467a

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 3831eb5bd7ba7630f27b64960e69ea89c6bb0eb83b92042d40ff841b1fe3b857
MD5 e547ca70d38932f6bd9fec3dc83cb66c
BLAKE2b-256 6f65d44be4e2d629a542b4e402fa90f8d1955012c29d18a5714251f02e7ce28e

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp39-cp39-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp39-cp39-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 96e4ed7f8a0d976d520cbbfeba7d160d0af0f421b961045fb02044617c224cb6
MD5 b10232dd57fa6d06803470fef594fc8e
BLAKE2b-256 10216b78b9e9cce55b0586219fa9453f0e6350330cbc487c63b8f733e814917b

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp38-cp38-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 97b95a8bd3593bbb15667af28d8eb98459203d6c8fdd8c84f7c8776ac8d1c03c
MD5 c0dfe3cf3bd3144ba60900d590da79f6
BLAKE2b-256 b5aee15a42c4a243d004fd9ee2a2f7863b090cb7823425021a4be21d98a6d46d

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 6610ad0a377174fece3551c9ac533ef4e794bb709015f8c8c0ab4904a77bc178
MD5 1a21c393fa881f0f137013b0e01111a6
BLAKE2b-256 5da0e269155f2121c4e7f61d8480a6a927a199aeeb34056e563ebfaedd30fa33

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp38-cp38-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp38-cp38-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 ddefeb4a395fd93e498480dee91dad567e982e9365774c84f186ca95748e9b48
MD5 d000a820e2e2b656bc26a44dd8450239
BLAKE2b-256 8d84396cfb2b20365a91ab297bbc9a722b4b471b7f04826b43f7c56095470f5d

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp37-cp37m-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 16b3d694fb4d7f153c1b554471c42bf172be5a8b3c90d626a50314f3ada62b08
MD5 37d525a08d7873934f1bf85794b8d821
BLAKE2b-256 e21701cfe6297a307f2ec4799e0065545461d59f58115424822da40e79ecb6d7

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 773b1cac86af0ebed4d26c503e92488eca3ec9b4bc4b4d8e7f69b0b38bf6bc0c
MD5 7cb09cd7578986f97cf0d726a31a1b4c
BLAKE2b-256 f1f15433d292a1c04085b4de5d0bd78f0bacdede6e4f917b57e68dcecb6e770a

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.2.0.20230728-cp37-cp37m-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.2.0.20230728-cp37-cp37m-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 9265f155078447d1c21ee2e17f00610a4c856597939cf96ae8430a2deaf7fdbe
MD5 c2d575af8f3580f15883b187dfc40fe3
BLAKE2b-256 01455d2b5bbeec8c83bd452f96e213eed9eb39c9674fffcf41e4f34b2816368f

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