rknn-toolkit2 2.1.0__tar.gz

rknn_toolkit2-2.1.0/LICENSE

@@ -0,0 +1,5 @@
+**Copyright Statement**
+
+Copyright(C) 2024 Rockchip Electronics Co., Ltd. All rights reserved.
+
+BY OPENING OR USING THIS FILE, RECEIVER HEREBY ACKNOWLEDGES AND AGREES THAT THE SOFTWARE/FIRMWARE AND ITS DOCUMENTATIONS ("ROCKCHIP SOFTWARE") RECEIVED FROM ROCKCHIP ON AN "AS-IS" BASIS ONLY WITHOUT ANY AND ALL WARRANTIES, EITHER EXPRESS, IMPLIED OR STATUTORY, INCLUDING, WITHOUT LIMITATION, ANY WARRANTY OR CONDITION WITH RESPECT TO TITLE, MERCHANTABILITY, FITNESS FOR ANY PARTICULAR PURPOSE, OR NON-INFRINGEMENT. NEITHER DOES ROCKCHIP PROVIDE ANY WARRANTY WHATSOEVER WITH RESPECT TO ANY OPEN SOURCE TECHNOLOGIES, THIRD-PARTY TECHNOLOGIES OR ANY STANDARD TECHNOLOGIES WHICH MAY BE SUPPORTED BY, INCORPORATED IN, OR SUPPLIED WITH THE ROCKCHIP SOFTWARE. RECEIVER EXPRESSLY ACKNOWLEDGES THAT IT IS RECEIVER'S SOLE RESPONSIBILITY TO OBTAIN AND MAINTAIN ALL NECESSARY LICENSES AND RIGHTS FROM THEIR RESPECTIVE OWNERS TO USE ANY SUCH THIRD-PARTY TECHNOLOGIES OR ANY STANDARD TECHNOLOGIES. RECEIVER'S SOLE AND EXCLUSIVE REMEDY AND ROCKCHIP'S ENTIRE AND CUMULATIVE LIABILITY WITH RESPECT TO THE ROCKCHIP SOFTWARE RELEASED HEREUNDER WILL BE, AT ROCKCHIP 'S OPTION, TO REVISE OR REPLACE THE ROCKCHIP SOFTWARE AT ISSUE, OR REFUND ANY FEES OR CHARGE PAID BY RECEIVER TO ROCKCHIP FOR SUCH ROCKCHIP SOFTWARE AT ISSUE.

rknn_toolkit2-2.1.0/PKG-INFO

@@ -0,0 +1,99 @@
+Metadata-Version: 2.1
+Name: rknn-toolkit2
+Version: 2.1.0
+Summary: RKNN Toolkit
+Home-page: https://github.com/airockchip/rknn-toolkit2
+Author: ai@rock-chips.com
+Author-email: airockchip <ai@rock-chips.com>
+Project-URL: Homepage, https://github.com/airockchip/rknn-toolkit2
+Project-URL: Issues, https://github.com/airockchip/rknn-toolkit2/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# Description
+  RKNN software stack can help users to quickly deploy AI models to Rockchip chips. The overall framework is as follows:
+    <center class="half">
+        <div style="background-color:#ffffff;">
+        <img src="res/framework.png" title="RKNN"/>
+    </center>
+
+  In order to use RKNPU, users need to first run the RKNN-Toolkit2 tool on the computer, convert the trained model into an RKNN format model, and then inference on the development board using the RKNN C API or Python API.
+
+- RKNN-Toolkit2 is a software development kit for users to perform model conversion, inference and performance evaluation on PC and Rockchip NPU platforms.
+
+- RKNN-Toolkit-Lite2 provides Python programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNN Runtime provides C/C++ programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNPU kernel driver is responsible for interacting with NPU hardware. It has been open source and can be found in the Rockchip kernel code.
+
+# Support Platform
+  - RK3588 Series
+  - RK3576 Series
+  - RK3566/RK3568 Series
+  - RK3562 Series
+  - RV1103/RV1106
+  - RV1103B
+  - RK2118
+
+
+Note:
+
+​      **For RK1808/RV1109/RV1126/RK3399Pro, please refer to :**
+
+​          https://github.com/airockchip/rknn-toolkit
+
+​          https://github.com/airockchip/rknpu
+
+​          https://github.com/airockchip/RK3399Pro_npu
+
+
+# Download
+- You can also download all packages, docker image, examples, docs and platform-tools from [RKNPU2_SDK](https://console.zbox.filez.com/l/I00fc3), fetch code: rknn
+- You can get more examples from [rknn mode zoo](https://github.com/airockchip/rknn_model_zoo)
+
+# Notes
+- RKNN-Toolkit2 is not compatible with [RKNN-Toolkit](https://github.com/airockchip/rknn-toolkit)
+- Currently only support on:
+  - Ubuntu 18.04 python 3.6/3.7
+  - Ubuntu 20.04 python 3.8/3.9
+  - Ubuntu 22.04 python 3.10/3.11
+- Latest version:v2.1.0
+
+
+
+# RKNN LLM
+
+If you want to deploy LLM (Large Language Model), we have introduced a new SDK called RKNN-LLM. For details, please refer to:
+
+https://github.com/airockchip/rknn-llm
+
+
+
+# CHANGELOG
+
+## v2.1.0
+ - Support RV1103B (Beta)
+- Support RK2118 (Beta)
+- Support Flash Attention (Only RK3562 and RK3576)
+- Improve MatMul API
+- Improve support for int32 and int64
+- Support more operators and operator fusion
+
+ for older version, please refer [CHANGELOG](CHANGELOG.md)
+
+# Feedback and Community Support
+- [Redmine](https://redmine.rock-chips.com) (**Feedback recommended, Please consult our sales or FAE for the redmine account**)
+- QQ Group Chat: 1025468710 (full, please join group 3)
+- QQ Group Chat2: 547021958 (full, please join group 3)
+- QQ Group Chat3: 469385426
+<center class="half">
+  <img width="200" height="200"  src="res/QQGroupQRCode.png" title="QQ Group Chat"/>
+  <img width="200" height="200"  src="res/QQGroup2QRCode.png" title="QQ Group Chat2"/>
+  <img width="200" height="200"  src="res/QQGroup3QRCode.png" title="QQ Group Chat3"/>
+</center>
+
+

rknn_toolkit2-2.1.0/README.md

@@ -0,0 +1,84 @@
+# Description
+  RKNN software stack can help users to quickly deploy AI models to Rockchip chips. The overall framework is as follows:
+    <center class="half">
+        <div style="background-color:#ffffff;">
+        <img src="res/framework.png" title="RKNN"/>
+    </center>
+
+  In order to use RKNPU, users need to first run the RKNN-Toolkit2 tool on the computer, convert the trained model into an RKNN format model, and then inference on the development board using the RKNN C API or Python API.
+
+- RKNN-Toolkit2 is a software development kit for users to perform model conversion, inference and performance evaluation on PC and Rockchip NPU platforms.
+
+- RKNN-Toolkit-Lite2 provides Python programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNN Runtime provides C/C++ programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNPU kernel driver is responsible for interacting with NPU hardware. It has been open source and can be found in the Rockchip kernel code.
+
+# Support Platform
+  - RK3588 Series
+  - RK3576 Series
+  - RK3566/RK3568 Series
+  - RK3562 Series
+  - RV1103/RV1106
+  - RV1103B
+  - RK2118
+
+
+Note:
+
+​      **For RK1808/RV1109/RV1126/RK3399Pro, please refer to :**
+
+​          https://github.com/airockchip/rknn-toolkit
+
+​          https://github.com/airockchip/rknpu
+
+​          https://github.com/airockchip/RK3399Pro_npu
+
+
+# Download
+- You can also download all packages, docker image, examples, docs and platform-tools from [RKNPU2_SDK](https://console.zbox.filez.com/l/I00fc3), fetch code: rknn
+- You can get more examples from [rknn mode zoo](https://github.com/airockchip/rknn_model_zoo)
+
+# Notes
+- RKNN-Toolkit2 is not compatible with [RKNN-Toolkit](https://github.com/airockchip/rknn-toolkit)
+- Currently only support on:
+  - Ubuntu 18.04 python 3.6/3.7
+  - Ubuntu 20.04 python 3.8/3.9
+  - Ubuntu 22.04 python 3.10/3.11
+- Latest version:v2.1.0
+
+
+
+# RKNN LLM
+
+If you want to deploy LLM (Large Language Model), we have introduced a new SDK called RKNN-LLM. For details, please refer to:
+
+https://github.com/airockchip/rknn-llm
+
+
+
+# CHANGELOG
+
+## v2.1.0
+ - Support RV1103B (Beta)
+- Support RK2118 (Beta)
+- Support Flash Attention (Only RK3562 and RK3576)
+- Improve MatMul API
+- Improve support for int32 and int64
+- Support more operators and operator fusion
+
+ for older version, please refer [CHANGELOG](CHANGELOG.md)
+
+# Feedback and Community Support
+- [Redmine](https://redmine.rock-chips.com) (**Feedback recommended, Please consult our sales or FAE for the redmine account**)
+- QQ Group Chat: 1025468710 (full, please join group 3)
+- QQ Group Chat2: 547021958 (full, please join group 3)
+- QQ Group Chat3: 469385426
+<center class="half">
+  <img width="200" height="200"  src="res/QQGroupQRCode.png" title="QQ Group Chat"/>
+  <img width="200" height="200"  src="res/QQGroup2QRCode.png" title="QQ Group Chat2"/>
+  <img width="200" height="200"  src="res/QQGroup3QRCode.png" title="QQ Group Chat3"/>
+</center>
+
+

rknn_toolkit2-2.1.0/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=50.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "rknn-toolkit2"
+version = "2.1.0"
+authors = [
+  { name="airockchip", email="ai@rock-chips.com" },
+]
+description = "RKNN Toolkit"
+readme = "README.md"
+requires-python = ">=3.6"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    'Operating System :: OS Independent',
+]
+
+[project.urls]
+Homepage = "https://github.com/airockchip/rknn-toolkit2"
+Issues = "https://github.com/airockchip/rknn-toolkit2/issues"

rknn_toolkit2-2.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

rknn_toolkit2-2.1.0/setup.py

@@ -0,0 +1,18 @@
+import setuptools
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="rknn-toolkit2",
+    version="2.1.0",
+    author="ai@rock-chips.com",
+    url='https://github.com/airockchip/rknn-toolkit2',
+    author_email="ai@rock-chips.com",
+    description="RKNN-TOOLKIT2  ",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    package_dir={"": "src"},
+    packages=setuptools.find_packages(where="src"),
+    python_requires=">=3.6",
+)

rknn_toolkit2-2.1.0/src/rknn_toolkit2.egg-info/PKG-INFO

@@ -0,0 +1,99 @@
+Metadata-Version: 2.1
+Name: rknn-toolkit2
+Version: 2.1.0
+Summary: RKNN Toolkit
+Home-page: https://github.com/airockchip/rknn-toolkit2
+Author: ai@rock-chips.com
+Author-email: airockchip <ai@rock-chips.com>
+Project-URL: Homepage, https://github.com/airockchip/rknn-toolkit2
+Project-URL: Issues, https://github.com/airockchip/rknn-toolkit2/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# Description
+  RKNN software stack can help users to quickly deploy AI models to Rockchip chips. The overall framework is as follows:
+    <center class="half">
+        <div style="background-color:#ffffff;">
+        <img src="res/framework.png" title="RKNN"/>
+    </center>
+
+  In order to use RKNPU, users need to first run the RKNN-Toolkit2 tool on the computer, convert the trained model into an RKNN format model, and then inference on the development board using the RKNN C API or Python API.
+
+- RKNN-Toolkit2 is a software development kit for users to perform model conversion, inference and performance evaluation on PC and Rockchip NPU platforms.
+
+- RKNN-Toolkit-Lite2 provides Python programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNN Runtime provides C/C++ programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.
+
+- RKNPU kernel driver is responsible for interacting with NPU hardware. It has been open source and can be found in the Rockchip kernel code.
+
+# Support Platform
+  - RK3588 Series
+  - RK3576 Series
+  - RK3566/RK3568 Series
+  - RK3562 Series
+  - RV1103/RV1106
+  - RV1103B
+  - RK2118
+
+
+Note:
+
+​      **For RK1808/RV1109/RV1126/RK3399Pro, please refer to :**
+
+​          https://github.com/airockchip/rknn-toolkit
+
+​          https://github.com/airockchip/rknpu
+
+​          https://github.com/airockchip/RK3399Pro_npu
+
+
+# Download
+- You can also download all packages, docker image, examples, docs and platform-tools from [RKNPU2_SDK](https://console.zbox.filez.com/l/I00fc3), fetch code: rknn
+- You can get more examples from [rknn mode zoo](https://github.com/airockchip/rknn_model_zoo)
+
+# Notes
+- RKNN-Toolkit2 is not compatible with [RKNN-Toolkit](https://github.com/airockchip/rknn-toolkit)
+- Currently only support on:
+  - Ubuntu 18.04 python 3.6/3.7
+  - Ubuntu 20.04 python 3.8/3.9
+  - Ubuntu 22.04 python 3.10/3.11
+- Latest version:v2.1.0
+
+
+
+# RKNN LLM
+
+If you want to deploy LLM (Large Language Model), we have introduced a new SDK called RKNN-LLM. For details, please refer to:
+
+https://github.com/airockchip/rknn-llm
+
+
+
+# CHANGELOG
+
+## v2.1.0
+ - Support RV1103B (Beta)
+- Support RK2118 (Beta)
+- Support Flash Attention (Only RK3562 and RK3576)
+- Improve MatMul API
+- Improve support for int32 and int64
+- Support more operators and operator fusion
+
+ for older version, please refer [CHANGELOG](CHANGELOG.md)
+
+# Feedback and Community Support
+- [Redmine](https://redmine.rock-chips.com) (**Feedback recommended, Please consult our sales or FAE for the redmine account**)
+- QQ Group Chat: 1025468710 (full, please join group 3)
+- QQ Group Chat2: 547021958 (full, please join group 3)
+- QQ Group Chat3: 469385426
+<center class="half">
+  <img width="200" height="200"  src="res/QQGroupQRCode.png" title="QQ Group Chat"/>
+  <img width="200" height="200"  src="res/QQGroup2QRCode.png" title="QQ Group Chat2"/>
+  <img width="200" height="200"  src="res/QQGroup3QRCode.png" title="QQ Group Chat3"/>
+</center>
+
+

rknn_toolkit2-2.1.0/src/rknn_toolkit2.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+setup.py
+src/rknn-toolkit2/__init__.py
+src/rknn_toolkit2.egg-info/PKG-INFO
+src/rknn_toolkit2.egg-info/SOURCES.txt
+src/rknn_toolkit2.egg-info/dependency_links.txt
+src/rknn_toolkit2.egg-info/top_level.txt

rknn_toolkit2-2.1.0/src/rknn_toolkit2.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

rknn_toolkit2-2.1.0/src/rknn_toolkit2.egg-info/top_level.txt

@@ -0,0 +1 @@
+rknn-toolkit2