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
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
2 maintainers
Release files for nncase 2.5.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 301.3 MB
Release files / nncase-2.5.1-cp310-cp310-win_amd64.whl
| Download URL | nncase-2.5.1-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 19.6 MB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
e494ee16cc32d03fce3597499c67d662fbb9b42f083a0c49f815e2c2edd1a79e
|
|
BLAKE2b-256 checksum How to use checksums |
8142439de08913f0d19d050a2252df7d0d9539ba7e534be61d27020b3a072e54
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.4 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
83f43561ce72ec79a427e1cac5e11c66fa294906befd3d369d87959ee0d3c130
|
|
BLAKE2b-256 checksum How to use checksums |
7508a23978a7939ce56da8af3f45af1c905d0eb6ac00284955ac00782732b250
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp310-cp310-macosx_10_15_x86_64.whl
| Download URL | nncase-2.5.1-cp310-cp310-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.3 MB |
| Tags | CPython 3.10 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
fe0657d3b1814d028332222b31fe222ef831651cd5066d5bba4e0c173e313714
|
|
BLAKE2b-256 checksum How to use checksums |
f319cfdcd520161f3e680ad932d5c3ae9616abc0f82a1715276cb1fbd0c9e5dc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp39-cp39-win_amd64.whl
| Download URL | nncase-2.5.1-cp39-cp39-win_amd64.whl |
|---|---|
| Size | 19.6 MB |
| Tags | CPython 3.9 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
3f2d65b9ab26ef8b7554a3c8209f50078e24f8280af0f44c5ff547bd99180c54
|
|
BLAKE2b-256 checksum How to use checksums |
88cc94234c0f98994db02a5ad56b678ce8f7721d59941e54125258a647e72f41
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.4 MB |
| Tags | CPython 3.9 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
53ed3cb92d9c9c1fa3173126ae69fba1ce4789b5356b3381f46dac7ca3b3c29c
|
|
BLAKE2b-256 checksum How to use checksums |
3ee16fb9c1ed32ba82b66684413d0d0f13e3ab731ef0062a9b27ae44129415f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp39-cp39-macosx_10_15_x86_64.whl
| Download URL | nncase-2.5.1-cp39-cp39-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.3 MB |
| Tags | CPython 3.9 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
e07bdc80667d5652aa78b7e4dae0e232fcc2bc413933dcb7ad9290f736dae64f
|
|
BLAKE2b-256 checksum How to use checksums |
037f01e9a0b30a79f9f24127af80972996bc484624b99a1e7a742cdffbc82d06
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp38-cp38-win_amd64.whl
| Download URL | nncase-2.5.1-cp38-cp38-win_amd64.whl |
|---|---|
| Size | 19.6 MB |
| Tags | CPython 3.8 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
a23c81a0d525f5523ff96272f8da4abb58acd73f21a56bc5c2da7f603152b395
|
|
BLAKE2b-256 checksum How to use checksums |
61716d212e6eb4379c62672665de2fea5b7a6b380e0ba703dff8b47460becf9a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.4 MB |
| Tags | CPython 3.8 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
54feb76c5eefe9af6b7bf8d91aec464efba1399d9b2e3211d18f4289018ca848
|
|
BLAKE2b-256 checksum How to use checksums |
91e668eb82e82a1a4bfe0d9b812a01aff14b956fec9c39ace62255da50dbcec1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp38-cp38-macosx_10_15_x86_64.whl
| Download URL | nncase-2.5.1-cp38-cp38-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.3 MB |
| Tags | CPython 3.8 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
69bcbdeb56d284ae281fe33708e6ad7e9dce996e842057fdd41a3df29a7cd6aa
|
|
BLAKE2b-256 checksum How to use checksums |
9c39ef878b7972421bba0e742f0d80176f099e2a056c5159e49db2d464ae5210
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp37-cp37m-win_amd64.whl
| Download URL | nncase-2.5.1-cp37-cp37m-win_amd64.whl |
|---|---|
| Size | 19.6 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Windows x86-64 |
|
SHA-256 checksum How to use checksums |
add153893c4d1c5a12c6b83aed572cfae0daeaeb8406063db81db0f45aff6e98
|
|
BLAKE2b-256 checksum How to use checksums |
1c0fc85e1d2317ce083d100785575d1f9a8a3419171d946811442d8d5f7a44a8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.5.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.4 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
fdb87a94b6633b9b73dc5b5765953383ecfbe855ffa526709a83fa70ef57a812
|
|
BLAKE2b-256 checksum How to use checksums |
8e998506bf93d6dc2ddf889641404ed9f8aca7e54ff702cb2d7290b81da34fe1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.5.1-cp37-cp37m-macosx_10_15_x86_64.whl
| Download URL | nncase-2.5.1-cp37-cp37m-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.3 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
87b8356fa86a36421434e55aedfe565b180ea700f8812561b940565661222143
|
|
BLAKE2b-256 checksum How to use checksums |
6221ee2610db41c6d0b39be50a3f5ce3b632b6d6dca32a14500337961c0ae177
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
