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
Metadata
2 maintainers
Release files for nncase 2.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 299.2 MB
Release files / nncase-2.4.0-cp310-cp310-win_amd64.whl
| Download URL | nncase-2.4.0-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 19.4 MB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
2d8221093f9f848cf5a9400f2aa399a2a0765807a85caf58f0244bde4eaee575
|
|
BLAKE2b-256 checksum How to use checksums |
db36f8835997eb5bf2029c36aaf19b2f4d73a5c848138aa8284a1d1e94461f30
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.3 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
263e45c1a0a2a7aae7e387e1e00bdc3ee818af88283e513564ec1255a3354990
|
|
BLAKE2b-256 checksum How to use checksums |
07573b5520c9dd7590bdec492c483aa9347d6f13c3d981ca32eaea2813e6eaf4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp310-cp310-macosx_10_15_x86_64.whl
| Download URL | nncase-2.4.0-cp310-cp310-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.1 MB |
| Tags | CPython 3.10 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
ad3ce5dae25f750aa953114742d6d9f5d77801bdd2560e3e42c2126cfbd3467d
|
|
BLAKE2b-256 checksum How to use checksums |
72c917d27e437957227c52922b17b54dc319289e0310d578f660a5cfd365cf62
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp39-cp39-win_amd64.whl
| Download URL | nncase-2.4.0-cp39-cp39-win_amd64.whl |
|---|---|
| Size | 19.4 MB |
| Tags | CPython 3.9 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
16194dfd1a4add86dc8c3110e113225ef49e1b1ac99351c30aae1a63742dbb7d
|
|
BLAKE2b-256 checksum How to use checksums |
a02c158d649250de82384dc13ee4572229e180c2ab2129fe1b54f4b88dbaf6c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.3 MB |
| Tags | CPython 3.9 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
398dc5f59af7142bd138b929c161e39c9eff581f29efdd4580560752b671fe7b
|
|
BLAKE2b-256 checksum How to use checksums |
b507d86ec82070475968d70cc32ac5b75e43f779c29184f129c354f744f21d48
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp39-cp39-macosx_10_15_x86_64.whl
| Download URL | nncase-2.4.0-cp39-cp39-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.1 MB |
| Tags | CPython 3.9 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
af5199eb8cb26d89e5cc38ec906ea6bfba602b4af66ff3cbb4acf34bd6f49359
|
|
BLAKE2b-256 checksum How to use checksums |
948cfb654d31345f9b1e471e81c422650dcc8cc53b7cff926aee22bdccc19105
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp38-cp38-win_amd64.whl
| Download URL | nncase-2.4.0-cp38-cp38-win_amd64.whl |
|---|---|
| Size | 19.4 MB |
| Tags | CPython 3.8 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
140cff156cd144c646f44f842e84c96ed689bab3599880c05e6c62ed2961c7fa
|
|
BLAKE2b-256 checksum How to use checksums |
b096ed2c473c1abb2c1c7dd9142761cf0a6f1ac3837cad4d6140c9985040f23f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.3 MB |
| Tags | CPython 3.8 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
997fdd3e7fcff7b1e0117062f3cfa0e1ac7ce3fec9e2e9c238d083ea98ef5160
|
|
BLAKE2b-256 checksum How to use checksums |
0bed392d64a58841c609c071be988ea0bc1fa900d77eef4978f7fb9601ceba44
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp38-cp38-macosx_10_15_x86_64.whl
| Download URL | nncase-2.4.0-cp38-cp38-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.1 MB |
| Tags | CPython 3.8 macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
7a4571780581da4e29f817e60de9c7a0b172ed857e943dfff94a8fcd7d43400d
|
|
BLAKE2b-256 checksum How to use checksums |
0c5ebf8bdd96ef960dc4822d14110d5902758c4d4c433c782741afc49f5f3960
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp37-cp37m-win_amd64.whl
| Download URL | nncase-2.4.0-cp37-cp37m-win_amd64.whl |
|---|---|
| Size | 19.4 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Windows x86-64 |
|
SHA-256 checksum How to use checksums |
b9d920796cbad7d85efe1421d1a969e3825960ee21ba38b9d890573e1a7a922f
|
|
BLAKE2b-256 checksum How to use checksums |
3d47be1686d4cec94fd1a6315af2fc281978778428dafb99bf5f35a8d161929e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | nncase-2.4.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 30.3 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
9e924e3fc14b329c671ddf633961c5a0c71142b5b320a5ad4235e34f26e66548
|
|
BLAKE2b-256 checksum How to use checksums |
b33466b82e956f804b88e4d6d447b0e8b57d8299d61433ec8141aaec464c5318
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
Release files / nncase-2.4.0-cp37-cp37m-macosx_10_15_x86_64.whl
| Download URL | nncase-2.4.0-cp37-cp37m-macosx_10_15_x86_64.whl |
|---|---|
| Size | 25.1 MB |
| Tags | CPython 3.7 CPython 3.7 pymalloc macOS 10.15+ x86-64 |
|
SHA-256 checksum How to use checksums |
ca687e0bd13df96d97a47aa8acce342269ad4904fa1bb36dfd4bd251e0d5371d
|
|
BLAKE2b-256 checksum How to use checksums |
4c6b1e35c46d7f8c5c8b7967bdd8f4704dbf70c9e366fac89050395cbc927881
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.7.5
|
