lemonade-sdk 8.0.4__tar.gz → 8.0.5__tar.gz

lemonade_sdk-8.0.5/PKG-INFO

@@ -0,0 +1,295 @@
+Metadata-Version: 2.4
+Name: lemonade-sdk
+Version: 8.0.5
+Summary: Lemonade SDK: Your LLM Aide for Validation and Deployment
+Author-email: lemonade@amd.com
+Requires-Python: >=3.10, <3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE.md
+Requires-Dist: invoke>=2.0.0
+Requires-Dist: onnx<1.18.0,>=1.11.0
+Requires-Dist: pyyaml>=5.4
+Requires-Dist: typeguard>=2.3.13
+Requires-Dist: packaging>=20.9
+Requires-Dist: numpy<2.0.0
+Requires-Dist: fasteners
+Requires-Dist: GitPython>=3.1.40
+Requires-Dist: psutil>=6.1.1
+Requires-Dist: wmi
+Requires-Dist: py-cpuinfo
+Requires-Dist: pytz
+Requires-Dist: zstandard
+Requires-Dist: fastapi
+Requires-Dist: uvicorn[standard]
+Requires-Dist: openai>=1.81.0
+Requires-Dist: transformers<=4.51.3
+Requires-Dist: jinja2
+Requires-Dist: tabulate
+Requires-Dist: sentencepiece
+Requires-Dist: huggingface-hub==0.33.0
+Provides-Extra: oga-hybrid
+Requires-Dist: onnx==1.16.1; extra == "oga-hybrid"
+Requires-Dist: numpy==1.26.4; extra == "oga-hybrid"
+Requires-Dist: protobuf>=6.30.1; extra == "oga-hybrid"
+Provides-Extra: oga-cpu
+Requires-Dist: onnxruntime-genai==0.8.2; extra == "oga-cpu"
+Requires-Dist: onnxruntime>=1.22.0; extra == "oga-cpu"
+Provides-Extra: dev
+Requires-Dist: torch>=2.6.0; extra == "dev"
+Requires-Dist: accelerate; extra == "dev"
+Requires-Dist: datasets; extra == "dev"
+Requires-Dist: pandas>=1.5.3; extra == "dev"
+Requires-Dist: matplotlib; extra == "dev"
+Requires-Dist: human-eval-windows==1.0.4; extra == "dev"
+Requires-Dist: lm-eval[api]; extra == "dev"
+Provides-Extra: oga-hybrid-minimal
+Requires-Dist: lemonade-sdk[oga-hybrid]; extra == "oga-hybrid-minimal"
+Provides-Extra: oga-cpu-minimal
+Requires-Dist: lemonade-sdk[oga-cpu]; extra == "oga-cpu-minimal"
+Provides-Extra: llm
+Requires-Dist: lemonade-sdk[dev]; extra == "llm"
+Provides-Extra: llm-oga-cpu
+Requires-Dist: lemonade-sdk[dev,oga-cpu]; extra == "llm-oga-cpu"
+Provides-Extra: llm-oga-igpu
+Requires-Dist: onnxruntime-genai-directml==0.6.0; extra == "llm-oga-igpu"
+Requires-Dist: onnxruntime-directml<1.22.0,>=1.19.0; extra == "llm-oga-igpu"
+Requires-Dist: transformers<4.45.0; extra == "llm-oga-igpu"
+Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-igpu"
+Provides-Extra: llm-oga-cuda
+Requires-Dist: onnxruntime-genai-cuda==0.8.2; extra == "llm-oga-cuda"
+Requires-Dist: onnxruntime-gpu>=1.22.0; extra == "llm-oga-cuda"
+Requires-Dist: transformers<=4.51.3; extra == "llm-oga-cuda"
+Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-cuda"
+Provides-Extra: llm-oga-npu
+Requires-Dist: onnx==1.16.0; extra == "llm-oga-npu"
+Requires-Dist: onnxruntime==1.18.0; extra == "llm-oga-npu"
+Requires-Dist: numpy==1.26.4; extra == "llm-oga-npu"
+Requires-Dist: protobuf>=6.30.1; extra == "llm-oga-npu"
+Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-npu"
+Provides-Extra: llm-oga-hybrid
+Requires-Dist: lemonade-sdk[dev,oga-hybrid]; extra == "llm-oga-hybrid"
+Provides-Extra: llm-oga-unified
+Requires-Dist: lemonade-sdk[llm-oga-hybrid]; extra == "llm-oga-unified"
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+## 🍋 Lemonade: Local LLM Serving with GPU and NPU acceleration
+
+<p align="center">
+  <a href="https://discord.gg/5xXzkMu8Zk">
+    <img src="https://img.shields.io/badge/Discord-7289DA?logo=discord&logoColor=white" alt="Discord" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/tree/main/test" title="Check out our tests">
+    <img src="https://github.com/lemonade-sdk/lemonade/actions/workflows/test_lemonade.yml/badge.svg" alt="Lemonade tests" />
+  </a>
+  <a href="docs/README.md#installation" title="Check out our instructions">
+    <img src="https://img.shields.io/badge/Windows-11-0078D6?logo=windows&logoColor=white" alt="Windows 11" />
+  </a>
+  <a href="https://lemonade-server.ai/#linux" title="Ubuntu 24.04 & 25.04 Supported">
+    <img src="https://img.shields.io/badge/Ubuntu-24.04%20%7C%2025.04-E95420?logo=ubuntu&logoColor=white" alt="Ubuntu 24.04 | 25.04" />
+  </a>
+  <a href="docs/README.md#installation" title="Check out our instructions">
+    <img src="https://img.shields.io/badge/Python-3.10%20%7C%203.12-blue?logo=python&logoColor=white" alt="Made with Python" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/blob/main/docs/contribute.md" title="Contribution Guide">
+    <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/releases/latest" title="Download the latest release">
+    <img src="https://img.shields.io/github/v/release/lemonade-sdk/lemonade?include_prereleases" alt="Latest Release" />
+  </a>
+  <a href="https://tooomm.github.io/github-release-stats/?username=lemonade-sdk&repository=lemonade">
+    <img src="https://img.shields.io/github/downloads/lemonade-sdk/lemonade/total.svg" alt="GitHub downloads" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/issues">
+    <img src="https://img.shields.io/github/issues/lemonade-sdk/lemonade" alt="GitHub issues" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-Apache-yellow.svg" alt="License: Apache" />
+  </a>
+  <a href="https://github.com/psf/black">
+    <img src="https://img.shields.io/badge/code%20style-black-000000.svg" alt="Code style: black" />
+  </a>
+  <a href="https://star-history.com/#lemonade-sdk/lemonade">
+    <img src="https://img.shields.io/badge/Star%20History-View-brightgreen" alt="Star History Chart" />
+  </a>
+</p>
+<p align="center">
+  <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/banner.png?raw=true" alt="Lemonade Banner" />
+</p>
+<h3 align="center">
+  <a href="https://lemonade-server.ai">Download</a> | 
+  <a href="https://lemonade-server.ai/docs/">Documentation</a> | 
+  <a href="https://discord.gg/5xXzkMu8Zk">Discord</a>
+</h3>
+
+Lemonade makes it easy to run Large Language Models (LLMs) on your PC. Our focus is using the best tools, such as neural processing units (NPUs) and Vulkan GPU acceleration, to maximize LLM speed and responsiveness.
+
+## Getting Started
+
+<div align="center">
+
+| Step 1: Download & Install | Step 2: Launch and Pull Models | Step 3: Start chatting! |
+|:---------------------------:|:-------------------------------:|:------------------------:|
+| <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/install.gif?raw=true" alt="Download & Install" width="245" /> | <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/launch_and_pull.gif?raw=true" alt="Launch and Pull Models" width="245" /> | <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/chat.gif?raw=true" alt="Start chatting!" width="245" /> |
+|Install using a [GUI](https://github.com/lemonade-sdk/lemonade/releases/latest/download/Lemonade_Server_Installer.exe) (Windows only), [pip](https://lemonade-server.ai/install_options.html), or [from source](https://lemonade-server.ai/install_options.html). |Use the [Model Manager](#model-library) to install models|A built-in chat interface is available!|
+</div>
+
+### Use it with your favorite OpenAI-compatible app!
+
+<p align="center">
+  <a href="https://lemonade-server.ai/docs/server/apps/open-webui/" title="Open WebUI" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/openwebui.jpg" alt="Open WebUI" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/continue/" title="Continue" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/continue_dev.png" alt="Continue" width="60" /></a>&nbsp;&nbsp;<a href="https://github.com/amd/gaia" title="Gaia" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/gaia.ico" alt="Gaia" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/anythingLLM/" title="AnythingLLM" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/anything_llm.png" alt="AnythingLLM" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/ai-dev-gallery/" title="AI Dev Gallery" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/ai_dev_gallery.webp" alt="AI Dev Gallery" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/lm-eval/" title="LM-Eval" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/lm_eval.png" alt="LM-Eval" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/codeGPT/" title="CodeGPT" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/codegpt.jpg" alt="CodeGPT" width="60" /></a>&nbsp;&nbsp;<a href="https://github.com/lemonade-sdk/lemonade/blob/main/docs/server/apps/ai-toolkit.md" title="AI Toolkit" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/ai_toolkit.png" alt="AI Toolkit" width="60" /></a>
+</p>
+
+> [!TIP]
+> Want your app featured here? Let's do it! Shoot us a message on [Discord](https://discord.gg/5xXzkMu8Zk), [create an issue](https://github.com/lemonade-sdk/lemonade/issues), or email lemonade@amd.com.
+
+## Using the CLI
+
+To run and chat with Gemma 3:
+
+```
+lemonade-server run Gemma-3-4b-it-GGUF
+```
+
+To install models ahead of time, use the `pull` command:
+
+```
+lemonade-server pull Gemma-3-4b-it-GGUF
+```
+
+To check all models available, use the `list` command:
+
+```
+lemonade-server list
+```
+
+> Note: If you installed from source, use the `lemonade-server-dev` command instead.
+
+## Model Library
+
+Lemonade supports both GGUF and ONNX models as detailed in the [Supported Configuration](#supported-configurations) section. A list of all built-in models is available [here](https://lemonade-server.ai/docs/server/models/).
+
+You can also import custom GGUF and ONNX models from Hugging Face by using our [Model Manager](http://localhost:8000/#model-management) (requires server to be running).
+<p align="center">
+  <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/model_manager.png?raw=true" alt="Model Manager" width="650" />
+</p>
+
+## Supported Configurations
+
+Lemonade supports the following configurations, while also making it easy to switch between them at runtime. Find more information about it [here](./docs/README.md#software-and-hardware-overview).
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2">Hardware</th>
+      <th colspan="3" align="center">🛠️ Engine Support</th>
+      <th colspan="2" align="center">🖥️ OS (x86/x64)</th>
+    </tr>
+    <tr>
+      <th align="center">OGA</th>
+      <th align="center">llamacpp</th>
+      <th align="center">HF</th>
+      <th align="center">Windows</th>
+      <th align="center">Linux</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><strong>🧠 CPU</strong></td>
+      <td align="center">All platforms</td>
+      <td align="center">All platforms</td>
+      <td align="center">All platforms</td>
+      <td align="center">✅</td>
+      <td align="center">✅</td>
+    </tr>
+    <tr>
+      <td><strong>🎮 GPU</strong></td>
+      <td align="center">—</td>
+      <td align="center">Vulkan: All platforms<br><small>Focus:<br/>Ryzen™ AI 7000/8000/300<br/>Radeon™ 7000/9000</small></td>
+      <td align="center">—</td>
+      <td align="center">✅</td>
+      <td align="center">✅</td>
+    </tr>
+    <tr>
+      <td><strong>🤖 NPU</strong></td>
+      <td align="center">AMD Ryzen™ AI 300 series</td>
+      <td align="center">—</td>
+      <td align="center">—</td>
+      <td align="center">✅</td>
+      <td align="center">—</td>
+    </tr>
+  </tbody>
+</table>
+
+
+## Integrate Lemonade Server with Your Application
+
+You can use any OpenAI-compatible client library by configuring it to use `http://localhost:8000/api/v1` as the base URL. A table containing official and popular OpenAI clients on different languages is shown below.
+
+Feel free to pick and choose your preferred language.
+
+
+| Python | C++ | Java | C# | Node.js | Go | Ruby | Rust | PHP |
+|--------|-----|------|----|---------|----|-------|------|-----|
+| [openai-python](https://github.com/openai/openai-python) | [openai-cpp](https://github.com/olrea/openai-cpp) | [openai-java](https://github.com/openai/openai-java) | [openai-dotnet](https://github.com/openai/openai-dotnet) | [openai-node](https://github.com/openai/openai-node) | [go-openai](https://github.com/sashabaranov/go-openai) | [ruby-openai](https://github.com/alexrudall/ruby-openai) | [async-openai](https://github.com/64bit/async-openai) | [openai-php](https://github.com/openai-php/client) |
+
+
+### Python Client Example
+```python
+from openai import OpenAI
+
+# Initialize the client to use Lemonade Server
+client = OpenAI(
+    base_url="http://localhost:8000/api/v1",
+    api_key="lemonade"  # required but unused
+)
+
+# Create a chat completion
+completion = client.chat.completions.create(
+    model="Llama-3.2-1B-Instruct-Hybrid",  # or any other available model
+    messages=[
+        {"role": "user", "content": "What is the capital of France?"}
+    ]
+)
+
+# Print the response
+print(completion.choices[0].message.content)
+```
+
+For more detailed integration instructions, see the [Integration Guide](./server_integration.md).
+
+## Beyond an LLM Server
+
+The [Lemonade SDK](./docs/README.md) also include the following components:
+
+- 🐍 **[Lemonade API](./docs/lemonade_api.md)**: High-level Python API to directly integrate Lemonade LLMs into Python applications.
+- 🖥️ **[Lemonade CLI](./docs/dev_cli/README.md)**: The `lemonade` CLI lets you mix-and-match LLMs (ONNX, GGUF, SafeTensors) with prompting templates, accuracy testing, performance benchmarking, and memory profiling to characterize your models on your hardware.
+
+## Contributing
+
+We are actively seeking collaborators from across the industry. If you would like to contribute to this project, please check out our [contribution guide](./docs/contribute.md).
+
+New contributors can find beginner-friendly issues tagged with "Good First Issue" to get started.
+
+<a href="https://github.com/lemonade-sdk/lemonade/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22">
+  <img src="https://img.shields.io/badge/🍋Lemonade-Good%20First%20Issue-yellowgreen?colorA=38b000&colorB=cccccc" alt="Good First Issue" />
+</a>
+
+## Maintainers
+
+This project is sponsored by AMD. It is maintained by @danielholanda @jeremyfowers @ramkrishna @vgodsoe in equal measure. You can reach us by filing an [issue](https://github.com/lemonade-sdk/lemonade/issues), email [lemonade@amd.com](mailto:lemonade@amd.com), or join our [Discord](https://discord.gg/5xXzkMu8Zk).
+
+## License
+
+This project is licensed under the [Apache 2.0 License](https://github.com/lemonade-sdk/lemonade/blob/main/LICENSE). Portions of the project are licensed as described in [NOTICE.md](./NOTICE.md).
+
+<!--This file was originally licensed under Apache 2.0. It has been modified.
+Modifications Copyright (c) 2025 AMD-->
+

lemonade_sdk-8.0.5/README.md

@@ -0,0 +1,213 @@
+## 🍋 Lemonade: Local LLM Serving with GPU and NPU acceleration
+
+<p align="center">
+  <a href="https://discord.gg/5xXzkMu8Zk">
+    <img src="https://img.shields.io/badge/Discord-7289DA?logo=discord&logoColor=white" alt="Discord" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/tree/main/test" title="Check out our tests">
+    <img src="https://github.com/lemonade-sdk/lemonade/actions/workflows/test_lemonade.yml/badge.svg" alt="Lemonade tests" />
+  </a>
+  <a href="docs/README.md#installation" title="Check out our instructions">
+    <img src="https://img.shields.io/badge/Windows-11-0078D6?logo=windows&logoColor=white" alt="Windows 11" />
+  </a>
+  <a href="https://lemonade-server.ai/#linux" title="Ubuntu 24.04 & 25.04 Supported">
+    <img src="https://img.shields.io/badge/Ubuntu-24.04%20%7C%2025.04-E95420?logo=ubuntu&logoColor=white" alt="Ubuntu 24.04 | 25.04" />
+  </a>
+  <a href="docs/README.md#installation" title="Check out our instructions">
+    <img src="https://img.shields.io/badge/Python-3.10%20%7C%203.12-blue?logo=python&logoColor=white" alt="Made with Python" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/blob/main/docs/contribute.md" title="Contribution Guide">
+    <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/releases/latest" title="Download the latest release">
+    <img src="https://img.shields.io/github/v/release/lemonade-sdk/lemonade?include_prereleases" alt="Latest Release" />
+  </a>
+  <a href="https://tooomm.github.io/github-release-stats/?username=lemonade-sdk&repository=lemonade">
+    <img src="https://img.shields.io/github/downloads/lemonade-sdk/lemonade/total.svg" alt="GitHub downloads" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/issues">
+    <img src="https://img.shields.io/github/issues/lemonade-sdk/lemonade" alt="GitHub issues" />
+  </a>
+  <a href="https://github.com/lemonade-sdk/lemonade/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-Apache-yellow.svg" alt="License: Apache" />
+  </a>
+  <a href="https://github.com/psf/black">
+    <img src="https://img.shields.io/badge/code%20style-black-000000.svg" alt="Code style: black" />
+  </a>
+  <a href="https://star-history.com/#lemonade-sdk/lemonade">
+    <img src="https://img.shields.io/badge/Star%20History-View-brightgreen" alt="Star History Chart" />
+  </a>
+</p>
+<p align="center">
+  <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/banner.png?raw=true" alt="Lemonade Banner" />
+</p>
+<h3 align="center">
+  <a href="https://lemonade-server.ai">Download</a> | 
+  <a href="https://lemonade-server.ai/docs/">Documentation</a> | 
+  <a href="https://discord.gg/5xXzkMu8Zk">Discord</a>
+</h3>
+
+Lemonade makes it easy to run Large Language Models (LLMs) on your PC. Our focus is using the best tools, such as neural processing units (NPUs) and Vulkan GPU acceleration, to maximize LLM speed and responsiveness.
+
+## Getting Started
+
+<div align="center">
+
+| Step 1: Download & Install | Step 2: Launch and Pull Models | Step 3: Start chatting! |
+|:---------------------------:|:-------------------------------:|:------------------------:|
+| <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/install.gif?raw=true" alt="Download & Install" width="245" /> | <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/launch_and_pull.gif?raw=true" alt="Launch and Pull Models" width="245" /> | <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/chat.gif?raw=true" alt="Start chatting!" width="245" /> |
+|Install using a [GUI](https://github.com/lemonade-sdk/lemonade/releases/latest/download/Lemonade_Server_Installer.exe) (Windows only), [pip](https://lemonade-server.ai/install_options.html), or [from source](https://lemonade-server.ai/install_options.html). |Use the [Model Manager](#model-library) to install models|A built-in chat interface is available!|
+</div>
+
+### Use it with your favorite OpenAI-compatible app!
+
+<p align="center">
+  <a href="https://lemonade-server.ai/docs/server/apps/open-webui/" title="Open WebUI" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/openwebui.jpg" alt="Open WebUI" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/continue/" title="Continue" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/continue_dev.png" alt="Continue" width="60" /></a>&nbsp;&nbsp;<a href="https://github.com/amd/gaia" title="Gaia" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/gaia.ico" alt="Gaia" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/anythingLLM/" title="AnythingLLM" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/anything_llm.png" alt="AnythingLLM" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/ai-dev-gallery/" title="AI Dev Gallery" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/ai_dev_gallery.webp" alt="AI Dev Gallery" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/lm-eval/" title="LM-Eval" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/lm_eval.png" alt="LM-Eval" width="60" /></a>&nbsp;&nbsp;<a href="https://lemonade-server.ai/docs/server/apps/codeGPT/" title="CodeGPT" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/codegpt.jpg" alt="CodeGPT" width="60" /></a>&nbsp;&nbsp;<a href="https://github.com/lemonade-sdk/lemonade/blob/main/docs/server/apps/ai-toolkit.md" title="AI Toolkit" target="_blank"><img src="https://raw.githubusercontent.com/lemonade-sdk/assets/refs/heads/main/partner_logos/ai_toolkit.png" alt="AI Toolkit" width="60" /></a>
+</p>
+
+> [!TIP]
+> Want your app featured here? Let's do it! Shoot us a message on [Discord](https://discord.gg/5xXzkMu8Zk), [create an issue](https://github.com/lemonade-sdk/lemonade/issues), or email lemonade@amd.com.
+
+## Using the CLI
+
+To run and chat with Gemma 3:
+
+```
+lemonade-server run Gemma-3-4b-it-GGUF
+```
+
+To install models ahead of time, use the `pull` command:
+
+```
+lemonade-server pull Gemma-3-4b-it-GGUF
+```
+
+To check all models available, use the `list` command:
+
+```
+lemonade-server list
+```
+
+> Note: If you installed from source, use the `lemonade-server-dev` command instead.
+
+## Model Library
+
+Lemonade supports both GGUF and ONNX models as detailed in the [Supported Configuration](#supported-configurations) section. A list of all built-in models is available [here](https://lemonade-server.ai/docs/server/models/).
+
+You can also import custom GGUF and ONNX models from Hugging Face by using our [Model Manager](http://localhost:8000/#model-management) (requires server to be running).
+<p align="center">
+  <img src="https://github.com/lemonade-sdk/assets/blob/main/docs/model_manager.png?raw=true" alt="Model Manager" width="650" />
+</p>
+
+## Supported Configurations
+
+Lemonade supports the following configurations, while also making it easy to switch between them at runtime. Find more information about it [here](./docs/README.md#software-and-hardware-overview).
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2">Hardware</th>
+      <th colspan="3" align="center">🛠️ Engine Support</th>
+      <th colspan="2" align="center">🖥️ OS (x86/x64)</th>
+    </tr>
+    <tr>
+      <th align="center">OGA</th>
+      <th align="center">llamacpp</th>
+      <th align="center">HF</th>
+      <th align="center">Windows</th>
+      <th align="center">Linux</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><strong>🧠 CPU</strong></td>
+      <td align="center">All platforms</td>
+      <td align="center">All platforms</td>
+      <td align="center">All platforms</td>
+      <td align="center">✅</td>
+      <td align="center">✅</td>
+    </tr>
+    <tr>
+      <td><strong>🎮 GPU</strong></td>
+      <td align="center">—</td>
+      <td align="center">Vulkan: All platforms<br><small>Focus:<br/>Ryzen™ AI 7000/8000/300<br/>Radeon™ 7000/9000</small></td>
+      <td align="center">—</td>
+      <td align="center">✅</td>
+      <td align="center">✅</td>
+    </tr>
+    <tr>
+      <td><strong>🤖 NPU</strong></td>
+      <td align="center">AMD Ryzen™ AI 300 series</td>
+      <td align="center">—</td>
+      <td align="center">—</td>
+      <td align="center">✅</td>
+      <td align="center">—</td>
+    </tr>
+  </tbody>
+</table>
+
+
+## Integrate Lemonade Server with Your Application
+
+You can use any OpenAI-compatible client library by configuring it to use `http://localhost:8000/api/v1` as the base URL. A table containing official and popular OpenAI clients on different languages is shown below.
+
+Feel free to pick and choose your preferred language.
+
+
+| Python | C++ | Java | C# | Node.js | Go | Ruby | Rust | PHP |
+|--------|-----|------|----|---------|----|-------|------|-----|
+| [openai-python](https://github.com/openai/openai-python) | [openai-cpp](https://github.com/olrea/openai-cpp) | [openai-java](https://github.com/openai/openai-java) | [openai-dotnet](https://github.com/openai/openai-dotnet) | [openai-node](https://github.com/openai/openai-node) | [go-openai](https://github.com/sashabaranov/go-openai) | [ruby-openai](https://github.com/alexrudall/ruby-openai) | [async-openai](https://github.com/64bit/async-openai) | [openai-php](https://github.com/openai-php/client) |
+
+
+### Python Client Example
+```python
+from openai import OpenAI
+
+# Initialize the client to use Lemonade Server
+client = OpenAI(
+    base_url="http://localhost:8000/api/v1",
+    api_key="lemonade"  # required but unused
+)
+
+# Create a chat completion
+completion = client.chat.completions.create(
+    model="Llama-3.2-1B-Instruct-Hybrid",  # or any other available model
+    messages=[
+        {"role": "user", "content": "What is the capital of France?"}
+    ]
+)
+
+# Print the response
+print(completion.choices[0].message.content)
+```
+
+For more detailed integration instructions, see the [Integration Guide](./server_integration.md).
+
+## Beyond an LLM Server
+
+The [Lemonade SDK](./docs/README.md) also include the following components:
+
+- 🐍 **[Lemonade API](./docs/lemonade_api.md)**: High-level Python API to directly integrate Lemonade LLMs into Python applications.
+- 🖥️ **[Lemonade CLI](./docs/dev_cli/README.md)**: The `lemonade` CLI lets you mix-and-match LLMs (ONNX, GGUF, SafeTensors) with prompting templates, accuracy testing, performance benchmarking, and memory profiling to characterize your models on your hardware.
+
+## Contributing
+
+We are actively seeking collaborators from across the industry. If you would like to contribute to this project, please check out our [contribution guide](./docs/contribute.md).
+
+New contributors can find beginner-friendly issues tagged with "Good First Issue" to get started.
+
+<a href="https://github.com/lemonade-sdk/lemonade/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22">
+  <img src="https://img.shields.io/badge/🍋Lemonade-Good%20First%20Issue-yellowgreen?colorA=38b000&colorB=cccccc" alt="Good First Issue" />
+</a>
+
+## Maintainers
+
+This project is sponsored by AMD. It is maintained by @danielholanda @jeremyfowers @ramkrishna @vgodsoe in equal measure. You can reach us by filing an [issue](https://github.com/lemonade-sdk/lemonade/issues), email [lemonade@amd.com](mailto:lemonade@amd.com), or join our [Discord](https://discord.gg/5xXzkMu8Zk).
+
+## License
+
+This project is licensed under the [Apache 2.0 License](https://github.com/lemonade-sdk/lemonade/blob/main/LICENSE). Portions of the project are licensed as described in [NOTICE.md](./NOTICE.md).
+
+<!--This file was originally licensed under Apache 2.0. It has been modified.
+Modifications Copyright (c) 2025 AMD-->
+

{lemonade_sdk-8.0.4 → lemonade_sdk-8.0.5}/setup.py

@@ -118,7 +118,7 @@ setup(
             "lemonade-server-dev=lemonade_server.cli:main",
         ]
     },
-    python_requires=">=3.10, <3.12",
+    python_requires=">=3.10, <3.13",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",
     include_package_data=True,

{lemonade_sdk-8.0.4 → lemonade_sdk-8.0.5}/src/lemonade/api.py

@@ -5,6 +5,11 @@ from lemonade.state import State
 import lemonade.common.printing as printing
 import lemonade.cache as cache
 from lemonade.tools.adapter import ModelAdapter, TokenizerAdapter
+from lemonade.common.system_info import (
+    get_system_info_dict,
+    get_device_info_dict,
+    get_system_info as get_system_info_obj,
+)
 
 
 class NotSupported(Exception):
@@ -121,5 +126,50 @@ def from_pretrained(
         _raise_not_supported(recipe, checkpoint)
 
 
+def get_system_info(verbose: bool = False) -> Dict:
+    """
+    Get comprehensive system information including hardware details and device information.
+
+    Returns:
+        dict: Complete system information including:
+            - Basic system info (OS, processor, memory, BIOS, etc.).
+            - Device information (CPU, AMD iGPU, AMD dGPU, NPU).
+            - Inference engine availability per device.
+            - Python package versions (verbose mode only).
+    """
+
+    # Get basic system info
+    info = get_system_info_dict()
+
+    # Add device information
+    info["Devices"] = get_device_info_dict()
+
+    # Filter out verbose-only information if not in verbose mode
+    if not verbose:
+        essential_keys = ["OS Version", "Processor", "Physical Memory", "Devices"]
+        info = {k: v for k, v in info.items() if k in essential_keys}
+    else:
+        # In verbose mode, add Python packages at the end
+        system_info_obj = get_system_info_obj()
+        info["Python Packages"] = system_info_obj.get_python_packages()
+
+    return info
+
+
+def get_device_info() -> Dict:
+    """
+    Get device information including CPU, AMD iGPU, AMD dGPU, and NPU details.
+
+    Returns:
+        dict: Device information including:
+            - cpu: CPU details with inference engine availability.
+            - amd_igpu: AMD integrated GPU information.
+            - amd_dgpu: List of AMD discrete GPU information.
+            - npu: NPU information.
+    """
+
+    return get_device_info_dict()
+
+
 # This file was originally licensed under Apache 2.0. It has been modified.
 # Modifications Copyright (c) 2025 AMD