Run local LLMs on iGPU, APU and CPU (AMD , Intel, and Qualcomm (Coming Soon)). Easiest way to launch OpenAI API Compatible Server on Windows, Linux and MacOS

* The Llama model architecture supports similar model families such as CodeLlama, Vicuna, Yi, and more.

+ The Mistral model architecture supports similar model families such as Zephyr.

• [2024/06] Support Phi-3 (mini, small, medium), Phi-3-Vision-Mini, Llama-2, Llama-3, Gemma (v1), Mistral v0.3, Starling-LM, Yi-1.5.
• [2024/06] Support vision/chat inference on iGPU, APU, CPU and CUDA.

• Supported Models
  • Onnxruntime Models
  • Ipex-LLM Models
• Getting Started
  • Installation From Source
  • Launch OpenAI API Compatible Server
  • Launch Chatbot Web UI
  • Launch Model Management UI
• Compile OpenAI-API Compatible Server into Windows Executable
• Prebuilt Binary (Alpha)
• Acknowledgements

• Windows

  1. Custom Setup:
  • IPEX(XPU): Requires anaconda environment. conda create -n ellm python=3.10 libuv; conda activate ellm.
  • DirectML: If you are using Conda Environment. Install additional dependencies: conda install conda-forge::vs2015_runtime.

  2. Install embeddedllm package. $env:ELLM_TARGET_DEVICE='directml'; pip install -e .. Note: currently support cpu, directml and cuda.

     • DirectML: $env:ELLM_TARGET_DEVICE='directml'; pip install -e .[directml]
     • CPU: $env:ELLM_TARGET_DEVICE='cpu'; pip install -e .[cpu]
     • CUDA: $env:ELLM_TARGET_DEVICE='cuda'; pip install -e .[cuda]
     • IPEX: $env:ELLM_TARGET_DEVICE='ipex'; python setup.py develop
     • OpenVINO: $env:ELLM_TARGET_DEVICE='openvino'; pip install -e .[openvino]
     • With Web UI:
       • DirectML: $env:ELLM_TARGET_DEVICE='directml'; pip install -e .[directml,webui]
       • CPU: $env:ELLM_TARGET_DEVICE='cpu'; pip install -e .[cpu,webui]
       • CUDA: $env:ELLM_TARGET_DEVICE='cuda'; pip install -e .[cuda,webui]
       • IPEX: $env:ELLM_TARGET_DEVICE='ipex'; python setup.py develop; pip install -r requirements-webui.txt
       • OpenVINO: $env:ELLM_TARGET_DEVICE='openvino'; pip install -e .[openvino,webui]

• Linux

  1. Custom Setup:
  • IPEX(XPU): Requires anaconda environment. conda create -n ellm python=3.10 libuv; conda activate ellm.
  • DirectML: If you are using Conda Environment. Install additional dependencies: conda install conda-forge::vs2015_runtime.

  2. Install embeddedllm package. ELLM_TARGET_DEVICE='directml' pip install -e .. Note: currently support cpu, directml and cuda.

     • DirectML: ELLM_TARGET_DEVICE='directml' pip install -e .[directml]
     • CPU: ELLM_TARGET_DEVICE='cpu' pip install -e .[cpu]
     • CUDA: ELLM_TARGET_DEVICE='cuda' pip install -e .[cuda]
     • IPEX: ELLM_TARGET_DEVICE='ipex' python setup.py develop
     • OpenVINO: ELLM_TARGET_DEVICE='openvino' pip install -e .[openvino]
     • With Web UI:
       • DirectML: ELLM_TARGET_DEVICE='directml' pip install -e .[directml,webui]
       • CPU: ELLM_TARGET_DEVICE='cpu' pip install -e .[cpu,webui]
       • CUDA: ELLM_TARGET_DEVICE='cuda' pip install -e .[cuda,webui]
       • IPEX: ELLM_TARGET_DEVICE='ipex' python setup.py develop; pip install -r requirements-webui.txt
       • OpenVINO: ELLM_TARGET_DEVICE='openvino' pip install -e .[openvino,webui]

1. Custom Setup:

   • Ipex

     • For Intel iGPU:

       set SYCL_CACHE_PERSISTENT=1
       set BIGDL_LLM_XMX_DISABLED=1

     • For Intel Arc™ A-Series Graphics:

       set SYCL_CACHE_PERSISTENT=1

2. ellm_server --model_path <path/to/model/weight>.

3. Example code to connect to the api server can be found in scripts/python. Note: To find out more of the supported arguments. ellm_server --help.

1. ellm_chatbot --port 7788 --host localhost --server_port <ellm_server_port> --server_host localhost. Note: To find out more of the supported arguments. ellm_chatbot --help.

It is an interface that allows you to download and deploy OpenAI API compatible server. You can find out the disk space required to download the model in the UI.

1. ellm_modelui --port 6678. Note: To find out more of the supported arguments. ellm_modelui --help.

NOTE: OpenVINO packaging currently uses torch==2.4.0. It will not be able to run due to missing dependencies which is libomp. Make sure to install libomp and add the libomp-xxxxxxx.dll to C:\\Windows\\System32.

1. Install embeddedllm.

2. Install PyInstaller: pip install pyinstaller==6.9.0.

3. Compile Windows Executable: pyinstaller .\ellm_api_server.spec.

4. You can find the executable in the dist\ellm_api_server.

5. Use it like ellm_server. .\ellm_api_server.exe --model_path <path/to/model/weight>.

   Powershell/Terminal Usage:

   ellm_server --model_path <path/to/model/weight>
   
   # DirectML
   ellm_server --model_path 'EmbeddedLLM_Phi-3-mini-4k-instruct-062024-onnx\onnx\directml\Phi-3-mini-4k-instruct-062024-int4' --port 5555
   
   # IPEX-LLM
   ellm_server --model_path '.\meta-llama_Meta-Llama-3.1-8B-Instruct\'  --backend 'ipex' --device 'xpu' --port 5555 --served_model_name 'meta-llama_Meta/Llama-3.1-8B-Instruct'
   
   # OpenVINO
   ellm_server --model_path '.\meta-llama_Meta-Llama-3.1-8B-Instruct\'  --backend 'openvino' --device 'gpu' --port 5555 --served_model_name 'meta-llama_Meta/Llama-3.1-8B-Instruct'

You can find the prebuilt OpenAI API Compatible Windows Executable in the Release page.

Powershell/Terminal Usage (Use it like ellm_server):

.\ellm_api_server.exe --model_path <path/to/model/weight>

# DirectML
.\ellm_api_server.exe --model_path 'EmbeddedLLM_Phi-3-mini-4k-instruct-062024-onnx\onnx\directml\Phi-3-mini-4k-instruct-062024-int4' --port 5555

# IPEX-LLM
.\ellm_api_server.exe --model_path '.\meta-llama_Meta-Llama-3.1-8B-Instruct\'  --backend 'ipex' --device 'xpu' --port 5555 --served_model_name 'meta-llama_Meta/Llama-3.1-8B-Instruct'

# OpenVINO
.\ellm_api_server.exe --model_path '.\meta-llama_Meta-Llama-3.1-8B-Instruct\'  --backend 'openvino' --device 'gpu' --port 5555 --served_model_name 'meta-llama_Meta/Llama-3.1-8B-Instruct'

• Excellent open-source projects: vLLM, onnxruntime-genai, Ipex-LLM and many others.