A neural network compiler for AI accelerators
Project description
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
Release history Release notifications | RSS feed
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
File details
Details for the file nncase-1.7.1.20220701-cp310-cp310-win_amd64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp310-cp310-win_amd64.whl
- Upload date:
- Size: 4.6 MB
- Tags: CPython 3.10, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 75c3c853d60fba8dc0ac688aa0e882a5d19db8f40c940073a32d2ba35a0d87fa |
|
| MD5 | dd613aa4ca00399afec8d3cf83bd0018 |
|
| BLAKE2b-256 | 1c9877c70840c68582af08a5d3aa6745c96d9f11591a41393f3af7a2d26b2196 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp310-cp310-manylinux_2_24_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp310-cp310-manylinux_2_24_x86_64.whl
- Upload date:
- Size: 9.8 MB
- Tags: CPython 3.10, manylinux: glibc 2.24+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 2620f62d265ea246d3471e996f23a6509b761b86d66a0433a9c469e890e9656c |
|
| MD5 | 1534ecec8e49a593425bdd5fd015acf4 |
|
| BLAKE2b-256 | 4a76770d2d6253bc3c5bbd9536fba7d693d779b65dac0f1969d0ec4d9f633656 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp310-cp310-macosx_10_15_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp310-cp310-macosx_10_15_x86_64.whl
- Upload date:
- Size: 7.8 MB
- Tags: CPython 3.10, macOS 10.15+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | e82dac8ebad0c24c80fe3d7e05c007be6f565b0707ff83cc7326f7541f16e542 |
|
| MD5 | d9c1d025fc65879fc818ad900ea7dfa1 |
|
| BLAKE2b-256 | beebbd6cbe0651d1d3a1b2c0a69504b223a63d2aa31c9890502e8157899ff131 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp39-cp39-win_amd64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp39-cp39-win_amd64.whl
- Upload date:
- Size: 4.6 MB
- Tags: CPython 3.9, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 1e7e907a95130124dd71be0883fb789dbfee8afff6cc06a22879d2da157a28c4 |
|
| MD5 | 559a9788fbb139f4fe37d286ea010c5b |
|
| BLAKE2b-256 | 2364b7ab9fb807e71cc3a6737e86a1feeed1daefe78c1a3ab4031e930f1ae765 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp39-cp39-manylinux_2_24_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp39-cp39-manylinux_2_24_x86_64.whl
- Upload date:
- Size: 9.8 MB
- Tags: CPython 3.9, manylinux: glibc 2.24+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | f1442b94689c13fcf02e347e6c755ee844849750eddc60230e8bdb69b9d3dd3f |
|
| MD5 | b173c80b49adca61f6fd32fabb00c582 |
|
| BLAKE2b-256 | 1976ae09b652aafd9023e3b55bc71c844dd17d1da7d20a71006cb2a2b64b7e16 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp39-cp39-macosx_10_15_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp39-cp39-macosx_10_15_x86_64.whl
- Upload date:
- Size: 7.8 MB
- Tags: CPython 3.9, macOS 10.15+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | cdc20fbac93928f1bb868bcd11e6eb498ea2ce8526833bd97ee1cfca3aee1d36 |
|
| MD5 | 1df48036fec094b38dc28b1543f48b18 |
|
| BLAKE2b-256 | 227ef27a0d1ec995c6f2aa73a8628c66e6b82d26ef40a9bbd58645f7c01de32c |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp38-cp38-win_amd64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp38-cp38-win_amd64.whl
- Upload date:
- Size: 4.6 MB
- Tags: CPython 3.8, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | bbddd8f1d92ed93272571d7657a93cf62196a24ff2bf690ba703dfbe375c6748 |
|
| MD5 | a3e0e0e4e6e275cb72db3777a4b4cc66 |
|
| BLAKE2b-256 | 1eefdfe9c0c49efee2cf07887e54cf3cdc06b3109d86fb41d5c3ce2aba3f0562 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp38-cp38-manylinux_2_24_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp38-cp38-manylinux_2_24_x86_64.whl
- Upload date:
- Size: 9.8 MB
- Tags: CPython 3.8, manylinux: glibc 2.24+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | b17d0f9b384ab1e40528293edb46bbe5a088be52777b7fc21e6fe92d09971eb0 |
|
| MD5 | 6d119ea1d57f574de229f4e4e83d6a1f |
|
| BLAKE2b-256 | df5b7e0542d60179b4c4de749fac8af7ab781897b4d1a0aed4ca98c76f30bf38 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp38-cp38-macosx_10_15_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp38-cp38-macosx_10_15_x86_64.whl
- Upload date:
- Size: 7.8 MB
- Tags: CPython 3.8, macOS 10.15+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 42f025f746bc4d302aa152043248fb1586e7ccfc7c1c3ca41390dd82b60663b2 |
|
| MD5 | d6b97e6b60928fe8099e650c9c069bbb |
|
| BLAKE2b-256 | 64d3ddc9bfb19805525f72ce9cd526d60462c1356e8bf9dae1fbda3a3cdf4cb0 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp37-cp37m-win_amd64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp37-cp37m-win_amd64.whl
- Upload date:
- Size: 4.6 MB
- Tags: CPython 3.7m, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 13a8a47107dcf099769d54591ba145a598731213d0ed97471be1bcb4bfc79f9d |
|
| MD5 | 7cfd669e5964ce6d993e41bc5e6f7b89 |
|
| BLAKE2b-256 | 742c018ddf20e95687609c01340445616e2068981905fb94a47d1ff6c46441a8 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp37-cp37m-manylinux_2_24_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp37-cp37m-manylinux_2_24_x86_64.whl
- Upload date:
- Size: 9.8 MB
- Tags: CPython 3.7m, manylinux: glibc 2.24+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d5d500f9ceb5779bc3e6945675e7d012c06c5bd9a2f7bef040770aa5bd4853c8 |
|
| MD5 | b1058d1319270c3ffc15477c21ea1a58 |
|
| BLAKE2b-256 | e611b5329156ceebe48938293d41b02a00fef320ebd5e8bc6cc578c5919475e7 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp37-cp37m-macosx_10_15_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp37-cp37m-macosx_10_15_x86_64.whl
- Upload date:
- Size: 7.8 MB
- Tags: CPython 3.7m, macOS 10.15+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d25b92a96bdfa7c9e97f7b39ff09bf6ba249c87eb0381ce0aa459e79f61ca8ca |
|
| MD5 | ccc6c8340837024a2704bd130b1b8e81 |
|
| BLAKE2b-256 | 6001bbe3e5fa4987bda51b1f452c9f76dc279e21ee4d5da48950730736665e31 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp36-cp36m-win_amd64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp36-cp36m-win_amd64.whl
- Upload date:
- Size: 4.6 MB
- Tags: CPython 3.6m, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 0b60ef9e14e30fc02aa59d1a5c68c50e6f8b48ba371695afe7fa16bb3e64f76a |
|
| MD5 | 3ed314e7d2f0eef506e824abe8acdb3d |
|
| BLAKE2b-256 | 7bae76b73fb59528291f40086aebc2f8f5b15d46a09f98f97f1eb70d6c348040 |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp36-cp36m-manylinux_2_24_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp36-cp36m-manylinux_2_24_x86_64.whl
- Upload date:
- Size: 9.8 MB
- Tags: CPython 3.6m, manylinux: glibc 2.24+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 1afa340ebc7a1d3c5a9fbf6c37f92c4e41be49f3c322ed5a56e00ce95499f79d |
|
| MD5 | 8e1c34ff3bd2ba757708d919d498896d |
|
| BLAKE2b-256 | 44f033dd68adb8b3f9ce16f96d96ffc86293e41b06ff6979ada617986c453edf |
Provenance
File details
Details for the file nncase-1.7.1.20220701-cp36-cp36m-macosx_10_15_x86_64.whl.
File metadata
- Download URL: nncase-1.7.1.20220701-cp36-cp36m-macosx_10_15_x86_64.whl
- Upload date:
- Size: 7.8 MB
- Tags: CPython 3.6m, macOS 10.15+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c2a279aaeb0006c3fd79dd9eac61486d7cc5a2511aba4554967bff6d597b7a9e |
|
| MD5 | 391aa03f0c62c69e956e24abc607b637 |
|
| BLAKE2b-256 | a60fa8f48547d6887f0ac1c10262a52d58d97691ac23fa808294ebd90fcdf8e3 |
