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

Usage

使用方法

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-2.0.0.20230602-cp310-cp310-win_amd64.whl (9.8 MB view details)

Uploaded CPython 3.10 Windows x86-64

nncase-2.0.0.20230602-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.1 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

nncase-2.0.0.20230602-cp310-cp310-macosx_10_15_x86_64.whl (11.8 MB view details)

Uploaded CPython 3.10 macOS 10.15+ x86-64

nncase-2.0.0.20230602-cp39-cp39-win_amd64.whl (9.8 MB view details)

Uploaded CPython 3.9 Windows x86-64

nncase-2.0.0.20230602-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.1 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

nncase-2.0.0.20230602-cp39-cp39-macosx_10_15_x86_64.whl (11.8 MB view details)

Uploaded CPython 3.9 macOS 10.15+ x86-64

nncase-2.0.0.20230602-cp38-cp38-win_amd64.whl (9.8 MB view details)

Uploaded CPython 3.8 Windows x86-64

nncase-2.0.0.20230602-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.1 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

nncase-2.0.0.20230602-cp38-cp38-macosx_10_15_x86_64.whl (11.8 MB view details)

Uploaded CPython 3.8 macOS 10.15+ x86-64

nncase-2.0.0.20230602-cp37-cp37m-win_amd64.whl (9.8 MB view details)

Uploaded CPython 3.7m Windows x86-64

nncase-2.0.0.20230602-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.1 MB view details)

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

nncase-2.0.0.20230602-cp37-cp37m-macosx_10_15_x86_64.whl (11.8 MB view details)

Uploaded CPython 3.7m macOS 10.15+ x86-64

File details

Details for the file nncase-2.0.0.20230602-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 c12606dc5204a3dc57e685622de1681542ff032dfeddf164a4cc551f2458aaea
MD5 6a6fbb971b28c506658a8c96fee3b125
BLAKE2b-256 6840541bbc9b57923b4fa904efe2e312c3d13ae270c52876053d33f8b13e4599

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 cfbb7fb9caf5abf8c57198e7c4a4bd0cc580186c3815d690bd74cccf407a5633
MD5 1388252961bb6e5ca988b20cac4cd6f2
BLAKE2b-256 83c6bcca7915992eea0847a2aa21f413f6b665ae0d1e4e8f3c5a7a5bd1306e4e

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp310-cp310-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp310-cp310-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 932c34b4dc0ed9564908668b2656a52a2903923e9b8e83853ff6ebc72a16f25b
MD5 0a49d50db8f50e0643d4c3def256cf88
BLAKE2b-256 fd8d05f91896b2c40722eb79cda649e91e0396090ee213b9d935c72eac1de399

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp39-cp39-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 1ed319448f0c683bf2bdb66b93af103bfb016188a027269622e6cec422471f2d
MD5 5a809e8c68d6d3cbe3a607ae325ea485
BLAKE2b-256 8fdd26723462be36e80e4d0f840c173f7e2781b8aaed07e41c4b64e72db8e169

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 86d17fae19e999534c68e22db8e24a0b358c9c70fb529eb0a64560405818682d
MD5 66759a808e346f5d52e606b9cf28dbc0
BLAKE2b-256 40e381f2f2c89e0e564a54872b0ec6f86dbc02a6775e5582fdc52ed75f9a3cb7

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp39-cp39-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp39-cp39-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 6c9b12a7aebc6c8eb3ef2b9c17a350466a0d0f1f8c31f27f790176dc386a987e
MD5 8c16e94c26aea4fa6726218fb5a5dc9b
BLAKE2b-256 7b1875194cba2105df28b2662ae11feac7f877e192a49a777453b54861a9e897

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp38-cp38-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 4753c17e726490e7018a0d89a1e2d002dec53d88b2da81d4c6854ddb325c65e5
MD5 e90fcfd96c9f7c5db09cb72cc231ede3
BLAKE2b-256 214da88ef128a2d67599699770dbcddf335eb7977d982719c82354cb018a6a0f

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 e84942f0ba898f9f94c8edf165251bd7ece8c0494f2c11e72e6de2d16e08fff4
MD5 33ed2d0e22af6effcdc544cce8e60f81
BLAKE2b-256 ab5de83f67935337901376067887f4da74cf31ae4c2c7463bec2cf8b690b50f0

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp38-cp38-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp38-cp38-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 7c49bbe085060f446e6d96c50ae95a413460802d2fb79220082e6bf71217a8e5
MD5 5ed715ec88cf37d8ac2686704749c00a
BLAKE2b-256 b64d866872b9f29f52edcea5435a755ec218da17aa9538cb1e7c00ed8f184281

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp37-cp37m-win_amd64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 335498bcd224f4a8257365f6b9959b0565e946545018ca5f8fcb76876e902dec
MD5 d64ea84d47175880f12e55e77eb35a1f
BLAKE2b-256 67fb22dcb65c36144cff1fe5fac6b0fb48a0f3a3b65a095fadd6aa6de3d3b66b

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 3b4147d3701ecece8b197c34db56e1838bbabdf72a6ced8eabe9c7a9db85383d
MD5 9d7b511ada9b0f1d55c5d06f0c43b455
BLAKE2b-256 5c68c5aa69c6adb97cd4183a9e98e4d3167400991f93673fc9cce89daebac141

See more details on using hashes here.

Provenance

File details

Details for the file nncase-2.0.0.20230602-cp37-cp37m-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for nncase-2.0.0.20230602-cp37-cp37m-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 3f34f75fb51defd72617ef867c543e16b454e5df1318b297f9e0d09b9cd633b3
MD5 5ebb57a00dd563645677c71ddb931ae9
BLAKE2b-256 9cc432df7685b363019fb5a7e25656896c41bc309084a2ab31f11915025eb02f

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