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
Usage
使用方法
Resources
资源
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
Metadata
2 maintainers
Release files for nncase 2.1.1.20230721
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 296.0 MB
Release files / nncase-2.1.1.20230721-cp310-cp310-win_amd64.whl
| Download URL | nncase-2.1.1.20230721-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 19.2 MB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
97acbb51d2812dcb617127550f00fbc187e72081cd1a4ccd279ae0e0a454cdaa
|
|
BLAKE2b-256 checksum How to use checksums |
5b46d9ab29a5ae44e505268dff88ea69993b3a1282e061079364b20ef3b89731
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.0 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
b13811bc4111f0b78488e2601ca0e96c41f098aeba0cd1596ae8511a4108c133
|
|
BLAKE2b-256 checksum How to use checksums |
cebb60b583609adea6be6cf77d572597b4525f769eb04ba0c7654bf57f53a13c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp310-cp310-macosx_10_15_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp310-cp310-macosx_10_15_x86_64.whl |
|---|---|
| Size | 24.8 MB |
| Tags | CPython 3.10 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
c732ada2e2b0a94cbb180881962f19a30b1700ecccb6a400d459df43b81fe1f6
|
|
BLAKE2b-256 checksum How to use checksums |
c77f95decfaed2de3bb57281ec21b7a4c48a6dee0f1826b11bc3fb27835fbb87
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp39-cp39-win_amd64.whl
| Download URL | nncase-2.1.1.20230721-cp39-cp39-win_amd64.whl |
|---|---|
| Size | 19.2 MB |
| Tags | CPython 3.9 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
1858fbcca8934dc16dccf778cdb7bdc4727de26159cf93eb38d5f62d9925ed48
|
|
BLAKE2b-256 checksum How to use checksums |
3384a834ae0b4d40c66cda7e858afd5baa8e442b2eecf203c37594f9c841abb8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.0 MB |
| Tags | CPython 3.9 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
7f4835abeec6a5b3d09f734f8eb6fa6d583dadf74c04eea2131b23f10461d48f
|
|
BLAKE2b-256 checksum How to use checksums |
50a85918a05abc6b95c5c0a8537920bbd97ade29ce15c40e782105ecc3b682fc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp39-cp39-macosx_10_15_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp39-cp39-macosx_10_15_x86_64.whl |
|---|---|
| Size | 24.8 MB |
| Tags | CPython 3.9 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
9954208c5d9c64453788d72b74ad73df65b4b4351ba9fb7b5c573bd72879a43e
|
|
BLAKE2b-256 checksum How to use checksums |
1c7f3598564186f9ea298f64c91938cb8a73fe58457d0b44e3640e5342bca932
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp38-cp38-win_amd64.whl
| Download URL | nncase-2.1.1.20230721-cp38-cp38-win_amd64.whl |
|---|---|
| Size | 19.2 MB |
| Tags | CPython 3.8 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
2e074c4c78e68adc7cd899746465ca96af03aa1fe8e4a11ea76587ad8f2a3578
|
|
BLAKE2b-256 checksum How to use checksums |
4134f21d8fc7fe38705bba845f5214afb1b5de17e4f7526f3392b37e513b30f4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.0 MB |
| Tags | CPython 3.8 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
5aa4a2a5556c4ac5afc130f44779fdeb5365847756522384b61709276978ce52
|
|
BLAKE2b-256 checksum How to use checksums |
d8ae938bc5f5aea360c48b9aed0f69399e5432feb73c4ae2500ba56c40bcbb27
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp38-cp38-macosx_10_15_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp38-cp38-macosx_10_15_x86_64.whl |
|---|---|
| Size | 24.8 MB |
| Tags | CPython 3.8 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
d5a4eb1465358f529a5558e46c3db50845d27d33a722a51b2e2482417981dffb
|
|
BLAKE2b-256 checksum How to use checksums |
b562d9b1235b12b7bcdb2df2c4e1829a8147a1492426cfc63f34f947dd95aacc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp37-cp37m-win_amd64.whl
| Download URL | nncase-2.1.1.20230721-cp37-cp37m-win_amd64.whl |
|---|---|
| Size | 19.2 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Windows x86-64 |
|
SHA-256 checksum How to use checksums |
6dd8ecdfc8625fb46857f2e39389323f3b40a60f1f1da4cecc7520b592cd5d35
|
|
BLAKE2b-256 checksum How to use checksums |
5a81062c350aa20c55a9c34cb4cbd7aee9f512924e58e322ddb6d4e13309eddc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.0 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
ce95b5949df923cb0fb794f8c4c74837bc0f7e5aac5474816f3cef997988ca40
|
|
BLAKE2b-256 checksum How to use checksums |
08190a27b57ce88685afc0ed00ae6c743c600cdc5b72628d74cab246b06af230
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.1.1.20230721-cp37-cp37m-macosx_10_15_x86_64.whl
| Download URL | nncase-2.1.1.20230721-cp37-cp37m-macosx_10_15_x86_64.whl |
|---|---|
| Size | 24.8 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
1166553a35f6677286d8ae44a574c7c9c46ec086e37221bdd9df5b98b50e8ab1
|
|
BLAKE2b-256 checksum How to use checksums |
edd2af0bcfd21c4ed4e161f813b94d44a783d9064bc0c89bde88e00c4e003d9b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Security for nncase 2.1.1.20230721
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
