llama.cpp/README.md

🦙 Python Bindings for llama.cpp

Simple Python bindings for @ggerganov's llama.cpp library. This package provides:

• Low-level access to C API via ctypes interface.
• High-level Python API for text completion
  • OpenAI-like API
  • LangChain compatibility
  • LlamaIndex compatibility
• OpenAI compatible web server
  • Local Copilot replacement
  • Function Calling support
  • Vision API support
  • Multiple Models

Documentation is available at https://llama-cpp-python.readthedocs.io/en/latest.

Installation

llama-cpp-python can be installed directly from PyPI as a source distribution by running:

pip install llama-cpp-python

This will build llama.cpp from source using cmake and your system's c compiler (required) and install the library alongside this python package.

If you run into issues during installation add the --verbose flag to the pip install command to see the full cmake build log.

Installation with Specific Hardware Acceleration (BLAS, CUDA, Metal, etc)

The default pip install behaviour is to build llama.cpp for CPU only on Linux and Windows and use Metal on MacOS.

llama.cpp supports a number of hardware acceleration backends depending including OpenBLAS, cuBLAS, CLBlast, HIPBLAS, and Metal. See the llama.cpp README for a full list of supported backends.

All of these backends are supported by llama-cpp-python and can be enabled by setting the CMAKE_ARGS environment variable before installing.

On Linux and Mac you set the CMAKE_ARGS like this:

CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python

On Windows you can set the CMAKE_ARGS like this:

$env:CMAKE_ARGS = "-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS"
pip install llama-cpp-python

OpenBLAS

To install with OpenBLAS, set the LLAMA_BLAS and LLAMA_BLAS_VENDOR environment variables before installing:

CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python

cuBLAS

To install with cuBLAS, set the LLAMA_CUBLAS=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python

Metal

To install with Metal (MPS), set the LLAMA_METAL=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

CLBlast

To install with CLBlast, set the LLAMA_CLBLAST=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python

hipBLAS

To install with hipBLAS / ROCm support for AMD cards, set the LLAMA_HIPBLAS=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python

Vulkan

To install with Vulkan support, set the LLAMA_VULKAN=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_VULKAN=on" pip install llama-cpp-python

Kompute

To install with Kompute support, set the LLAMA_KOMPUTE=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_KOMPUTE=on" pip install llama-cpp-python

SYCL

To install with SYCL support, set the LLAMA_SYCL=on environment variable before installing:

CMAKE_ARGS="-DLLAMA_SYCL=on" pip install llama-cpp-python

Windows Notes

If you run into issues where it complains it can't find 'nmake' '?' or CMAKE_C_COMPILER, you can extract w64devkit as mentioned in llama.cpp repo and add those manually to CMAKE_ARGS before running pip install:

$env:CMAKE_GENERATOR = "MinGW Makefiles"
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on -DCMAKE_C_COMPILER=C:/w64devkit/bin/gcc.exe -DCMAKE_CXX_COMPILER=C:/w64devkit/bin/g++.exe"

See the above instructions and set CMAKE_ARGS to the BLAS backend you want to use.

MacOS Notes

Detailed MacOS Metal GPU install documentation is available at docs/install/macos.md

M1 Mac Performance Issue

Note: If you are using Apple Silicon (M1) Mac, make sure you have installed a version of Python that supports arm64 architecture. For example:

wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-MacOSX-arm64.sh
bash Miniforge3-MacOSX-arm64.sh

Otherwise, while installing it will build the llama.cpp x86 version which will be 10x slower on Apple Silicon (M1) Mac.

M Series Mac Error: (mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64'))

Try installing with

CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DLLAMA_METAL=on" pip install --upgrade --verbose --force-reinstall --no-cache-dir llama-cpp-python

Upgrading and Reinstalling

To upgrade or rebuild llama-cpp-python add the following flags to ensure that the package is rebuilt correctly:

pip install llama-cpp-python  --upgrade --force-reinstall --no-cache-dir

This will ensure that all source files are re-built with the most recently set CMAKE_ARGS flags.

High-level API

API Reference

The high-level API provides a simple managed interface through the Llama class.

Below is a short example demonstrating how to use the high-level API to for basic text completion:

>>> from llama_cpp import Llama
>>> llm = Llama(
      model_path="./models/7B/llama-model.gguf",
      # n_gpu_layers=-1, # Uncomment to use GPU acceleration
      # seed=1337, # Uncomment to set a specific seed
      # n_ctx=2048, # Uncomment to increase the context window
)
>>> output = llm(
      "Q: Name the planets in the solar system? A: ", # Prompt
      max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
      stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
      echo=True # Echo the prompt back in the output
) # Generate a completion, can also call create_completion
>>> print(output)
{
  "id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "object": "text_completion",
  "created": 1679561337,
  "model": "./models/7B/llama-model.gguf",
  "choices": [
    {
      "text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
      "index": 0,
      "logprobs": None,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 28,
    "total_tokens": 42
  }
}

Text completion is available through the __call__ and create_completion methods of the Llama class.

Chat Completion

The high-level API also provides a simple interface for chat completion.

Note that chat_format option must be set for the particular model you are using.

>>> from llama_cpp import Llama
>>> llm = Llama(
      model_path="path/to/llama-2/llama-model.gguf",
      chat_format="llama-2"
)
>>> llm.create_chat_completion(
      messages = [
          {"role": "system", "content": "You are an assistant who perfectly describes images."},
          {
              "role": "user",
              "content": "Describe this image in detail please."
          }
      ]
)

Chat completion is available through the create_chat_completion method of the Llama class.

JSON and JSON Schema Mode

If you want to constrain chat responses to only valid JSON or a specific JSON Schema you can use the response_format argument to the create_chat_completion method.

JSON Mode

The following example will constrain the response to be valid JSON.

>>> from llama_cpp import Llama
>>> llm = Llama(model_path="path/to/model.gguf", chat_format="chatml")
>>> llm.create_chat_completion(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant that outputs in JSON.",
        },
        {"role": "user", "content": "Who won the world series in 2020"},
    ],
    response_format={
        "type": "json_object",
    },
    temperature=0.7,
)

JSON Schema Mode

To constrain the response to a specific JSON Schema, you can use the schema property of the response_format argument.

>>> from llama_cpp import Llama
>>> llm = Llama(model_path="path/to/model.gguf", chat_format="chatml")
>>> llm.create_chat_completion(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant that outputs in JSON.",
        },
        {"role": "user", "content": "Who won the world series in 2020"},
    ],
    response_format={
        "type": "json_object",
        "schema": {
            "type": "object",
            "properties": {"team_name": {"type": "string"}},
            "required": ["team_name"],
        },
    },
    temperature=0.7,
)

Function Calling

The high-level API also provides a simple interface for function calling.

The only set of models that supports full function calling at this time is functionary. The various gguf-converted files for this set of models can be found here. Functionary is able to intelligently call functions and also analyze any provided function outputs to generate coherent responses. All v2 models of functionary supports parallel function calling. You can provide either functionary-v1 or functionary-v2 for the chat_format when initializing the Llama class.

Note that due to discrepancies between llama.cpp and HuggingFace's tokenizers, it is required to provide HF Tokenizer for functionary. The LlamaHFTokenizer class can be initialized and passed into the Llama class. This will override the default llama.cpp tokenizer used in Llama class. The tokenizer files are already included in the respective HF repositories hosting the gguf files.

>>> from llama_cpp import Llama, LlamaHFTokenizer
>>> tokenizer = LlamaHFTokenizer.from_pretrained("path/to/functionary/")
>>> llm = Llama(model_path="path/to/functionary/llama-model.gguf", tokenizer=tokenizer, chat_format="functionary-v2")
>>> llm.create_chat_completion(
      messages = [
        {
          "role": "user",
          "content": "Extract Jason is 25 years old"
        }
      ],
      tools=[{
        "type": "function",
        "function": {
          "name": "UserDetail",
          "parameters": {
            "type": "object",
            "title": "UserDetail",
            "properties": {
              "name": {
                "title": "Name",
                "type": "string"
              },
              "age": {
                "title": "Age",
                "type": "integer"
              }
            },
            "required": [ "name", "age" ]
          }
        }
      }],
      tool_choice={
        "type": "function",
        "function": {
          "name": "UserDetail"
        }
      },
)

Multi-modal Models

llama-cpp-python supports the llava1.5 family of multi-modal models which allow the language model to read information from both text and images.

You'll first need to download one of the available multi-modal models in GGUF format:

• llava-v1.5-7b
• llava-v1.5-13b
• bakllava-1-7b

Then you'll need to use a custom chat handler to load the clip model and process the chat messages and images.

>>> from llama_cpp import Llama
>>> from llama_cpp.llama_chat_format import Llava15ChatHandler
>>> chat_handler = Llava15ChatHandler(clip_model_path="path/to/llava/mmproj.bin")
>>> llm = Llama(
  model_path="./path/to/llava/llama-model.gguf",
  chat_handler=chat_handler,
  n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
  logits_all=True,# needed to make llava work
)
>>> llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are an assistant who perfectly describes images."},
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "https://.../image.png"}},
                {"type" : "text", "text": "Describe this image in detail please."}
            ]
        }
    ]
)

Speculative Decoding

llama-cpp-python supports speculative decoding which allows the model to generate completions based on a draft model.

The fastest way to use speculative decoding is through the LlamaPromptLookupDecoding class.

Just pass this as a draft model to the Llama class during initialization.

from llama_cpp import Llama
from llama_cpp.llama_speculative import LlamaPromptLookupDecoding

llama = Llama(
    model_path="path/to/model.gguf",
    draft_model=LlamaPromptLookupDecoding(num_pred_tokens=10) # num_pred_tokens is the number of tokens to predict 10 is the default and generally good for gpu, 2 performs better for cpu-only machines.
)

Adjusting the Context Window

The context window of the Llama models determines the maximum number of tokens that can be processed at once. By default, this is set to 512 tokens, but can be adjusted based on your requirements.

For instance, if you want to work with larger contexts, you can expand the context window by setting the n_ctx parameter when initializing the Llama object:

llm = Llama(model_path="./models/7B/llama-model.gguf", n_ctx=2048)

OpenAI Compatible Web Server

llama-cpp-python offers a web server which aims to act as a drop-in replacement for the OpenAI API. This allows you to use llama.cpp compatible models with any OpenAI compatible client (language libraries, services, etc).

To install the server package and get started:

pip install llama-cpp-python[server]
python3 -m llama_cpp.server --model models/7B/llama-model.gguf

Similar to Hardware Acceleration section above, you can also install with GPU (cuBLAS) support like this:

CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python[server]
python3 -m llama_cpp.server --model models/7B/llama-model.gguf --n_gpu_layers 35

Navigate to http://localhost:8000/docs to see the OpenAPI documentation.

To bind to 0.0.0.0 to enable remote connections, use python3 -m llama_cpp.server --host 0.0.0.0. Similarly, to change the port (default is 8000), use --port.

You probably also want to set the prompt format. For chatml, use

python3 -m llama_cpp.server --model models/7B/llama-model.gguf --chat_format chatml

That will format the prompt according to how model expects it. You can find the prompt format in the model card. For possible options, see llama_cpp/llama_chat_format.py and look for lines starting with "@register_chat_format".

Web Server Features

• Local Copilot replacement
• Function Calling support
• Vision API support
• Multiple Models

Docker image

A Docker image is available on GHCR. To run the server:

docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/llama-model.gguf ghcr.io/abetlen/llama-cpp-python:latest

Docker on termux (requires root) is currently the only known way to run this on phones, see termux support issue

Low-level API

API Reference

The low-level API is a direct ctypes binding to the C API provided by llama.cpp. The entire low-level API can be found in llama_cpp/llama_cpp.py and directly mirrors the C API in llama.h.

Below is a short example demonstrating how to use the low-level API to tokenize a prompt:

>>> import llama_cpp
>>> import ctypes
>>> llama_cpp.llama_backend_init(numa=False) # Must be called once at the start of each program
>>> params = llama_cpp.llama_context_default_params()
# use bytes for char * params
>>> model = llama_cpp.llama_load_model_from_file(b"./models/7b/llama-model.gguf", params)
>>> ctx = llama_cpp.llama_new_context_with_model(model, params)
>>> max_tokens = params.n_ctx
# use ctypes arrays for array params
>>> tokens = (llama_cpp.llama_token * int(max_tokens))()
>>> n_tokens = llama_cpp.llama_tokenize(ctx, b"Q: Name the planets in the solar system? A: ", tokens, max_tokens, add_bos=llama_cpp.c_bool(True))
>>> llama_cpp.llama_free(ctx)

Check out the examples folder for more examples of using the low-level API.

Documentation

Documentation is available via https://llama-cpp-python.readthedocs.io/. If you find any issues with the documentation, please open an issue or submit a PR.

Development

This package is under active development and I welcome any contributions.

To get started, clone the repository and install the package in editable / development mode:

git clone --recurse-submodules https://github.com/abetlen/llama-cpp-python.git
cd llama-cpp-python

# Upgrade pip (required for editable mode)
pip install --upgrade pip

# Install with pip
pip install -e .

# if you want to use the fastapi / openapi server
pip install -e .[server]

# to install all optional dependencies
pip install -e .[all]

# to clear the local build cache
make clean

You can also test out specific commits of lama.cpp by checking out the desired commit in the vendor/llama.cpp submodule and then running make clean and pip install -e . again. Any changes in the llama.h API will require changes to the llama_cpp/llama_cpp.py file to match the new API (additional changes may be required elsewhere).

FAQ

Are there pre-built binaries / binary wheels available?

The recommended installation method is to install from source as described above. The reason for this is that llama.cpp is built with compiler optimizations that are specific to your system. Using pre-built binaries would require disabling these optimizations or supporting a large number of pre-built binaries for each platform.

That being said there are some pre-built binaries available through the Releases as well as some community provided wheels.

In the future, I would like to provide pre-built binaries and wheels for common platforms and I'm happy to accept any useful contributions in this area. This is currently being tracked in #741

How does this compare to other Python bindings of llama.cpp?

I originally wrote this package for my own use with two goals in mind:

• Provide a simple process to install llama.cpp and access the full C API in llama.h from Python
• Provide a high-level Python API that can be used as a drop-in replacement for the OpenAI API so existing apps can be easily ported to use llama.cpp

Any contributions and changes to this package will be made with these goals in mind.

License

This project is licensed under the terms of the MIT license.