- Using the commands in the [`tests`](tests) folder. For instance, running the `./tests/test-backend-ops` command tests different backend implementations of the GGML library
- Execute [the full CI locally on your machine](ci/README.md) before publishing
- Please rate the complexity of your PR (i.e. `Review Complexity : Low`, `Review Complexity : Medium`, `Review Complexity : High`). This makes it easier for maintainers to triage the PRs.
- The PR template has a series of review complexity checkboxes `[ ]` that [you can mark as](https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/about-task-lists)`[X]` for your convenience
- Consider allowing write access to your branch for faster review
- If your PR becomes stale, don't hesitate to ping the maintainers in the comments
# Pull requests (for collaborators)
- Squash-merge PRs
- Use the following format for the squashed commit title: `<module> : <commit title> (#<issue_number>)`. For example: `utils : fix typo in utils.py (#1234)`
- Optionally, pick a `<module>` from here: https://github.com/ggerganov/llama.cpp/wiki/Modules
# Coding guidelines
- Avoid adding third-party dependencies, extra files, extra headers, etc.
- Always consider cross-compatibility with other operating systems and architectures
- Avoid fancy looking modern STL constructs, use basic `for` loops, avoid templates, keep it simple
- There are no strict rules for the code style, but try to follow the patterns in the code (indentation, spaces, etc.). Vertical alignment makes things more readable and easier to batch edit
- Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line, `void * ptr`, `int & a`
- Naming usually optimizes for common prefix (see https://github.com/ggerganov/ggml/pull/302#discussion_r1243240963)
- Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices
- Matrix multiplication is unconventional: [`C = ggml_mul_mat(ctx, A, B)`](https://github.com/ggerganov/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064) means $C^T = A B^T \Leftrightarrow C = B A^T.$
# Legacy build targets that were renamed in #7809, but we want to build binaries that for them that output a deprecation warning if people try to use them.
# We don't want to clutter things too much, so we only build replacements for the most commonly used binaries.
LEGACY_TARGETS_BUILD= main quantize perplexity embedding server
$(error I ERROR:For CUDA versions < 11.7 a target CUDA architecture must be explicitly provided via environment variable CUDA_DOCKER_ARCH, e.g. by running "export CUDA_DOCKER_ARCH=compute_XX" on Unix-like systems, where XX is the minimum compute capability that the code needs to run on. A list with compute capabilities can be found here: https://developer.nvidia.com/cuda-gpus )
Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others) in pure C/C++
### Recent API changes
> [!IMPORTANT]
[2024 Jun 12] Binaries have been renamed w/ a `llama-` prefix. `main` is now `llama-cli`, `server` is `llama-server`, etc (https://github.com/ggerganov/llama.cpp/pull/7809)
## Recent API changes
- [2024 Jun 26] The source code and CMake build scripts have been restructured https://github.com/ggerganov/llama.cpp/pull/8006
- [2024 Apr 21] `llama_token_to_piece` can now optionally render special tokens https://github.com/ggerganov/llama.cpp/pull/6807
- [2024 Apr 4] State and session file functions reorganized under `llama_state_*` https://github.com/ggerganov/llama.cpp/pull/6341
- [2024 Mar 26] Logits and embeddings API updated for compactness https://github.com/ggerganov/llama.cpp/pull/6122
...
...
@@ -20,9 +24,10 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
- [2024 Mar 4] Embeddings API updated https://github.com/ggerganov/llama.cpp/pull/5796
- [2024 Mar 3] `struct llama_context_params` https://github.com/ggerganov/llama.cpp/pull/5849
-**`convert.py` has been deprecated and moved to `examples/convert_legacy_llama.py`, please use `convert_hf_to_gguf.py`** https://github.com/ggerganov/llama.cpp/pull/7430
[llama.cpp web server](./examples/server) is a lightweight [OpenAI API](https://github.com/openai/openai-openapi) compatible HTTP server that can be used to serve local models and easily connect them to existing clients.
- PHP (API bindings and features built on top of llama.cpp): [distantmagic/resonance](https://github.com/distantmagic/resonance)[(more info)](https://github.com/ggerganov/llama.cpp/pull/6326)
-[AI Sublime Text plugin](https://github.com/yaroslavyaroslav/OpenAI-sublime-text)(MIT)
-[AIKit](https://github.com/sozercan/aikit)(MIT)
-[LARS - The LLM & Advanced Referencing Solution](https://github.com/abgulati/LARS)(AGPL)
*(to have a project listed here, it should clearly state that it depends on `llama.cpp`)*
**Tools:**
-[akx/ggify](https://github.com/akx/ggify) – download PyTorch models from HuggingFace Hub and convert them to GGML
-[crashr/gppm](https://github.com/crashr/gppm) – launch llama.cpp instances utilizing NVIDIA Tesla P40 or P100 GPUs with reduced idle power consumption
**Infrastructure:**
---
-[Paddler](https://github.com/distantmagic/paddler) - Stateful load balancer custom-tailored for llama.cpp
Here is a typical run using LLaMA v2 13B on M2 Ultra:
**Games:**
-[Lucy's Labyrinth](https://github.com/MorganRO8/Lucys_Labyrinth) - A simple maze game where agents controlled by an AI model will try to trick you.
## Demo
<details>
<summary>Typical run using LLaMA v2 13B on M2 Ultra</summary>
```
$ make -j && ./main -m models/llama-13b-v2/ggml-model-q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
$ make -j && ./llama-cli -m models/llama-13b-v2/ggml-model-q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
I llama.cpp build info:
I UNAME_S: Darwin
I UNAME_P: arm
...
...
@@ -291,550 +277,85 @@ llama_print_timings: eval time = 24513.59 ms / 399 runs ( 61.44 ms
llama_print_timings: total time = 25431.49 ms
```
</details>
<details>
<summary>Demo of running both LLaMA-7B and whisper.cpp on a single M1 Pro MacBook</summary>
And here is another demo of running both LLaMA-7B and [whisper.cpp](https://github.com/ggerganov/whisper.cpp) on a single M1 Pro MacBook:
Here are the end-to-end binary build and model conversion steps for most supported models.
### Get the Code
```bash
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
```
### Build
In order to build llama.cpp you have four different options.
- Using `make`:
- On Linux or MacOS:
```bash
make
```
- On Windows:
1. Download the latest fortran version of [w64devkit](https://github.com/skeeto/w64devkit/releases).
2. Extract `w64devkit` on your pc.
3. Run `w64devkit.exe`.
4. Use the `cd` command to reach the `llama.cpp` folder.
5. From here you can run:
```bash
make
```
### Basic usage
- Notes:
- For faster compilation, add the `-j` argument to run multiple jobs in parallel. For example, `make -j 8` will run 8 jobs in parallel.
- For faster repeated compilation, install [ccache](https://ccache.dev/).
- For debug builds, run `make LLAMA_DEBUG=1`
Firstly, you need to get the binary. There are different methods that you can follow:
- Method 1: Clone this repository and build locally, see [how to build](./docs/build.md)
- Method 2: If you are using MacOS or Linux, you can install llama.cpp via [brew, flox or nix](./docs/install.md)
- Method 3: Use a Docker image, see [documentation for Docker](./docs/docker.md)
- Method 4: Download pre-built binary from [releases](https://github.com/ggerganov/llama.cpp/releases)
- Using `CMake`:
You can run a basic completion using this command:
```bash
cmake -B build
cmake --build build --config Release
```
**Notes**:
- For faster compilation, add the `-j` argument to run multiple jobs in parallel. For example, `cmake --build build --config Release -j 8` will run 8 jobs in parallel.
- For faster repeated compilation, install [ccache](https://ccache.dev/).
- For debug builds, there are two cases:
1. Single-config generators (e.g. default = `Unix Makefiles`; note that they just ignore the `--config` flag):
```bash
cmake -B build -DCMAKE_BUILD_TYPE=Debug
cmake --build build
```
2. Multi-config generators (`-G` param set to Visual Studio, XCode...):
```bash
cmake -B build -G "Xcode"
cmake --build build --config Debug
```
- Using `Zig` (version 0.11 or later):
Building for optimization levels and CPU features can be accomplished using standard build arguments, for example AVX2, FMA, F16C,
it's also possible to cross compile for other operating systems and architectures:
**Notes:** With this packages you can build llama.cpp with OPENBLAS and
CLBLAST support for use OpenCL GPU acceleration in FreeBSD. Please read
the instructions for use and activate this options in this document below.
### Homebrew
```bash
llama-cli -m your_model.gguf -p"I believe the meaning of life is"-n 128
On Mac and Linux, the homebrew package manager can be used via
# Output:
# I believe the meaning of life is to find your own truth and to live in accordance with it. For me, this means being true to myself and following my passions, even if they don't align with societal expectations. I think that's what I love about yoga – it's not just a physical practice, but a spiritual one too. It's about connecting with yourself, listening to your inner voice, and honoring your own unique journey.
```
brew install llama.cpp
```
The formula is automatically updated with new `llama.cpp` releases.
### Metal Build
On MacOS, Metal is enabled by default. Using Metal makes the computation run on the GPU.
To disable the Metal build at compile time use the `LLAMA_NO_METAL=1` flag or the `LLAMA_METAL=OFF` cmake option.
When built with Metal support, you can explicitly disable GPU inference with the `--n-gpu-layers|-ngl 0` command-line
argument.
### BLAS Build
Building the program with BLAS support may lead to some performance improvements in prompt processing using batch sizes higher than 32 (the default is 512). Support with CPU-only BLAS implementations doesn't affect the normal generation performance. We may see generation performance improvements with GPU-involved BLAS implementations, e.g. cuBLAS, hipBLAS and CLBlast. There are currently several different BLAS implementations available for build and use:
- #### Accelerate Framework:
This is only available on Mac PCs and it's enabled by default. You can just build using the normal instructions.
- #### OpenBLAS:
This provides BLAS acceleration using only the CPU. Make sure to have OpenBLAS installed on your machine.
See [this page](./examples/main/README.md) for a full list of parameters.
- Using `make`:
- On Linux:
```bash
make LLAMA_OPENBLAS=1
```
### Conversation mode
- On Windows:
1. Download the latest fortran version of [w64devkit](https://github.com/skeeto/w64devkit/releases).
2. Download the latest version of [OpenBLAS for Windows](https://github.com/xianyi/OpenBLAS/releases).
3. Extract `w64devkit` on your pc.
4. From the OpenBLAS zip that you just downloaded copy `libopenblas.a`, located inside the `lib` folder, inside `w64devkit\x86_64-w64-mingw32\lib`.
5. From the same OpenBLAS zip copy the content of the `include` folder inside `w64devkit\x86_64-w64-mingw32\include`.
6. Run `w64devkit.exe`.
7. Use the `cd` command to reach the `llama.cpp` folder.
Check [BLIS.md](docs/BLIS.md) for more information.
- #### SYCL
SYCL is a higher-level programming model to improve programming productivity on various hardware accelerators.
llama.cpp based on SYCL is used to **support Intel GPU** (Data Center Max series, Flex series, Arc series, Built-in GPU and iGPU).
For detailed info, please refer to [llama.cpp for SYCL](README-sycl.md).
- #### Intel oneMKL
Building through oneAPI compilers will make avx_vnni instruction set available for intel processors that do not support avx512 and avx512_vnni. Please note that this build config **does not support Intel GPU**. For Intel GPU support, please refer to [llama.cpp for SYCL](./README-sycl.md).
- Using manual oneAPI installation:
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. Otherwise please install oneAPI and follow the below steps:
```bash
source /opt/intel/oneapi/setvars.sh # You can skip this step if in oneapi-basekit docker image, only required for manual installation
If you do not want to source the environment vars and install oneAPI manually, you can also build the code using intel docker container: [oneAPI-basekit](https://hub.docker.com/r/intel/oneapi-basekit). Then, you can use the commands given above.
Check [Optimizing and Running LLaMA2 on Intel® CPU](https://www.intel.com/content/www/us/en/content-details/791610/optimizing-and-running-llama2-on-intel-cpu.html) for more information.
- #### CUDA
This provides GPU acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager (e.g. `apt install nvidia-cuda-toolkit`) or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).
For Jetson user, if you have Jetson Orin, you can try this: [Offical Support](https://www.jetson-ai-lab.com/tutorial_text-generation.html). If you are using an old model(nano/TX2), need some additional operations before compiling.
- Using `make`:
```bash
make LLAMA_CUDA=1
```
- Using `CMake`:
```bash
cmake -B build -DLLAMA_CUDA=ON
cmake --build build --config Release
```
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used. The following compilation options are also available to tweak performance:
| LLAMA_CUDA_FORCE_DMMV | Boolean | false | Force the use of dequantization + matrix vector multiplication kernels instead of using kernels that do matrix vector multiplication on quantized data. By default the decision is made based on compute capability (MMVQ for 6.1/Pascal/GTX 1000 or higher). Does not affect k-quants. |
| LLAMA_CUDA_DMMV_X | Positive integer >= 32 | 32 | Number of values in x direction processed by the CUDA dequantization + matrix vector multiplication kernel per iteration. Increasing this value can improve performance on fast GPUs. Power of 2 heavily recommended. Does not affect k-quants. |
| LLAMA_CUDA_MMV_Y | Positive integer | 1 | Block size in y direction for the CUDA mul mat vec kernels. Increasing this value can improve performance on fast GPUs. Power of 2 recommended. |
| LLAMA_CUDA_FORCE_MMQ | Boolean | false | Force the use of dequantization + matrix multiplication kernels instead of leveraging Math libraries. | |
| LLAMA_CUDA_F16 | Boolean | false | If enabled, use half-precision floating point arithmetic for the CUDA dequantization + mul mat vec kernels and for the q4_1 and q5_1 matrix matrix multiplication kernels. Can improve performance on relatively recent GPUs. |
| LLAMA_CUDA_KQUANTS_ITER | 1 or 2 | 2 | Number of values processed per iteration and per CUDA thread for Q2_K and Q6_K quantization formats. Setting this value to 1 can improve performance for slow GPUs. |
| LLAMA_CUDA_PEER_MAX_BATCH_SIZE | Positive integer | 128 | Maximum batch size for which to enable peer access between multiple GPUs. Peer access requires either Linux or NVLink. When using NVLink enabling peer access for larger batch sizes is potentially beneficial. |
- #### hipBLAS
This provides BLAS acceleration on HIP-supported AMD GPUs.
Make sure to have ROCm installed.
You can download it from your Linux distro's package manager or from here: [ROCm Quick Start (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html#rocm-install-quick).
- Using `make`:
```bash
make LLAMA_HIPBLAS=1
```
- Using `CMake` for Linux (assuming a gfx1030-compatible AMD GPU):
On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting `-DLLAMA_HIP_UMA=ON`.
However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).
Note that if you get the following error:
```
clang: error: cannot find ROCm device library; provide its path via '--rocm-path' or '--rocm-device-lib-path', or pass '-nogpulib' to build without ROCm device library
```
Try searching for a directory under `HIP_PATH` that contains the file
`oclc_abi_version_400.bc`. Then, add the following to the start of the
command: `HIP_DEVICE_LIB_PATH=<directory-you-just-found>`, so something
Make sure that `AMDGPU_TARGETS` is set to the GPU arch you want to compile for. The above example uses `gfx1100` that corresponds to Radeon RX 7900XTX/XT/GRE. You can find a list of targets [here](https://llvm.org/docs/AMDGPUUsage.html#processors)
Find your gpu version string by matching the most significant version information from `rocminfo | grep gfx | head -1 | awk '{print $2}'` with the list of processors, e.g. `gfx1035` maps to `gfx1030`.
The environment variable [`HIP_VISIBLE_DEVICES`](https://rocm.docs.amd.com/en/latest/understand/gpu_isolation.html#hip-visible-devices) can be used to specify which GPU(s) will be used.
If your GPU is not officially supported you can use the environment variable [`HSA_OVERRIDE_GFX_VERSION`] set to a similar GPU, for example 10.3.0 on RDNA2 (e.g. gfx1030, gfx1031, or gfx1035) or 11.0.0 on RDNA3.
The following compilation options are also available to tweak performance (yes, they refer to CUDA, not HIP, because it uses the same code as the cuBLAS version above):
| LLAMA_CUDA_DMMV_X | Positive integer >= 32 | 32 | Number of values in x direction processed by the HIP dequantization + matrix vector multiplication kernel per iteration. Increasing this value can improve performance on fast GPUs. Power of 2 heavily recommended. Does not affect k-quants. |
| LLAMA_CUDA_MMV_Y | Positive integer | 1 | Block size in y direction for the HIP mul mat vec kernels. Increasing this value can improve performance on fast GPUs. Power of 2 recommended. Does not affect k-quants. |
| LLAMA_CUDA_KQUANTS_ITER | 1 or 2 | 2 | Number of values processed per iteration and per HIP thread for Q2_K and Q6_K quantization formats. Setting this value to 1 can improve performance for slow GPUs. |
- #### CLBlast
OpenCL acceleration is provided by the matrix multiplication kernels from the [CLBlast](https://github.com/CNugteren/CLBlast) project and custom kernels for ggml that can generate tokens on the GPU.
You will need the [OpenCL SDK](https://github.com/KhronosGroup/OpenCL-SDK).
- For Ubuntu, Debian, and Fedora the packages `opencl-headers`, `ocl-icd` may be needed.
- For Windows, a pre-built SDK is available on the [OpenCL Releases](https://github.com/KhronosGroup/OpenCL-SDK/releases) page.
- <details>
<summary>Installing the OpenCL SDK from source</summary>
Pre-built CLBlast binaries may be found on the [CLBlast Releases](https://github.com/CNugteren/CLBlast/releases) page. For Unix variants, it may also be found in your operating system's packages.
Linux packaging:
Fedora Linux:
```bash
sudo dnf install clblast
```
Alternatively, they may be built from source.
-<details>
<summary>Windows:</summary>
```cmd
set OPENCL_SDK_ROOT="C:/OpenCL-SDK-v2023.04.17-Win-x64"
docker run -it--rm-v"$(pwd):/app:Z"--device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 llama-cpp-vulkan -m"/app/models/YOUR_MODEL_FILE"-p"Building a website can be done in 10 simple steps:"-n 400 -e-ngl 33
```
**Without docker**:
Firstly, you need to make sure you have installed [Vulkan SDK](https://vulkan.lunarg.com/doc/view/latest/linux/getting_started_ubuntu.html)
For example, on Ubuntu 22.04 (jammy), use the command below:
# To verify the installation, use the command below:
vulkaninfo
```
Alternatively your package manager might be able to provide the appropiate libraries. For example for Ubuntu 22.04 you can install `libvulkan-dev` instead.
Then, build llama.cpp using the cmake command below:
```bash
cmake -B build -DLLAMA_VULKAN=1
cmake --build build --config Release
# Test the output binary (with "-ngl 33" to offload all layers to GPU)
./bin/main -m"PATH_TO_MODEL"-p"Hi you how are you"-n 50 -e-ngl 33 -t 4
# You should see in the output, ggml_vulkan detected your GPU. For example:
> You can use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space on Hugging Face to quantise your model weights without any setup too. It is synced from `llama.cpp` main every 6 hours.
To obtain the official LLaMA 2 weights please see the <ahref="#obtaining-and-using-the-facebook-llama-2-model">Obtaining and using the Facebook LLaMA 2 model</a> section. There is also a large selection of pre-quantized `gguf` models available on Hugging Face.
Note: `convert.py` has been moved to `examples/convert-legacy-llama.py` and shouldn't be used for anything other than `Llama/Llama2/Mistral` models and their derievatives.
It does not support LLaMA 3, you can use `convert-hf-to-gguf.py` with LLaMA 3 downloaded from Hugging Face.
If you want a more ChatGPT-like experience, you can run in conversation mode by passing `-cnv` as a parameter:
```bash
# obtain the official LLaMA model weights and place them in ./models
llama-cli -m your_model.gguf -p"You are a helpful assistant"-cnv
# Output:
# > hi, who are you?
# Hi there! I'm your helpful assistant! I'm an AI-powered chatbot designed to assist and provide information to users like you. I'm here to help answer your questions, provide guidance, and offer support on a wide range of topics. I'm a friendly and knowledgeable AI, and I'm always happy to help with anything you need. What's on your mind, and how can I assist you today?
#
# > what is 1+1?
# Easy peasy! The answer to 1+1 is... 2!
```
### Run the quantized model
By default, the chat template will be taken from the input model. If you want to use another chat template, pass `--chat-template NAME` as a parameter. See the list of [supported templates](https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template)
./llama-cli -m your_model.gguf -p"You are a helpful assistant"-cnv--chat-template chatml
```
When running the larger models, make sure you have enough disk space to store all the intermediate files.
### Running on Windows with prebuilt binaries
You will find prebuilt Windows binaries on the release page.
You can also use your own template via in-prefix, in-suffix and reverse-prompt parameters:
Simply download and extract the latest zip package of choice: (e.g. `llama-b1380-bin-win-avx2-x64.zip`)
From the unzipped folder, open a terminal/cmd window here and place a pre-converted `.gguf` model file. Test out the main example like so:
```
.\main -m llama-2-7b.Q4_0.gguf -n 128
```bash
./llama-cli -m your_model.gguf -p"You are a helpful assistant"-cnv--in-prefix'User: '--reverse-prompt'User:'
```
### Memory/Disk Requirements
As the models are currently fully loaded into memory, you will need adequate disk space to save them and sufficient RAM to load them. At the moment, memory and disk requirements are the same.
| Model | Original size | Quantized size (Q4_0) |
|------:|--------------:|----------------------:|
| 7B | 13 GB | 3.9 GB |
| 13B | 24 GB | 7.8 GB |
| 30B | 60 GB | 19.5 GB |
| 65B | 120 GB | 38.5 GB |
### Quantization
Several quantization methods are supported. They differ in the resulting model disk size and inference speed.
-[quantization tuning](https://github.com/ggerganov/llama.cpp/pull/5320), [another one](https://github.com/ggerganov/llama.cpp/pull/5334), and [another one](https://github.com/ggerganov/llama.cpp/pull/5361)
### Perplexity (measuring model quality)
### Web server
You can use the `perplexity` example to measure perplexity over a given prompt (lower perplexity is better).
For more information, see [https://huggingface.co/docs/transformers/perplexity](https://huggingface.co/docs/transformers/perplexity).
[llama.cpp web server](./examples/server/README.md) is a lightweight [OpenAI API](https://github.com/openai/openai-openapi) compatible HTTP server that can be used to serve local models and easily connect them to existing clients.
The perplexity measurements in table above are done against the `wikitext2` test dataset (https://paperswithcode.com/dataset/wikitext-2), with context length of 512.
The time per token is measured on a MacBook M1 Pro 32GB RAM using 4 and 8 threads.
perplexity : calculating perplexity over 655 chunks
24.43 seconds per pass - ETA 4.45 hours
[1]4.5970,[2]5.1807,[3]6.0382,...
```
And after 4.45 hours, you will have the final perplexity.
### Interactive mode
If you want a more ChatGPT-like experience, you can run in interactive mode by passing `-i` as a parameter.
> [!NOTE]
> If you prefer basic usage, please consider using conversation mode instead of interactive mode
In this mode, you can always interrupt generation by pressing Ctrl+C and entering one or more lines of text, which will be converted into tokens and appended to the current context. You can also specify a *reverse prompt* with the parameter `-r "reverse prompt string"`. This will result in user input being prompted whenever the exact tokens of the reverse prompt string are encountered in the generation. A typical use is to use a prompt that makes LLaMA emulate a chat between multiple users, say Alice and Bob, and pass `-r "Alice:"`.
Here is an example of a few-shot interaction, invoked with the command
...
...
@@ -847,16 +368,16 @@ Here is an example of a few-shot interaction, invoked with the command
Note the use of `--color` to distinguish between user input and generated text. Other parameters are explained in more detail in the [README](examples/main/README.md) for the `main` example program.
Note the use of `--color` to distinguish between user input and generated text. Other parameters are explained in more detail in the [README](examples/main/README.md) for the `llama-cli` example program.
The prompt, user inputs, and model generations can be saved and resumed across calls to `./main` by leveraging `--prompt-cache` and `--prompt-cache-all`. The `./examples/chat-persistent.sh` script demonstrates this with support for long-running, resumable chat sessions. To use this example, you must provide a file to cache the initial chat prompt and a directory to save the chat session, and may optionally provide the same variables as `chat-13B.sh`. The same prompt cache can be reused for new chat sessions. Note that both prompt cache and chat directory are tied to the initial prompt (`PROMPT_TEMPLATE`) and the model file.
The prompt, user inputs, and model generations can be saved and resumed across calls to `./llama-cli` by leveraging `--prompt-cache` and `--prompt-cache-all`. The `./examples/chat-persistent.sh` script demonstrates this with support for long-running, resumable chat sessions. To use this example, you must provide a file to cache the initial chat prompt and a directory to save the chat session, and may optionally provide the same variables as `chat-13B.sh`. The same prompt cache can be reused for new chat sessions. Note that both prompt cache and chat directory are tied to the initial prompt (`PROMPT_TEMPLATE`) and the model file.
`llama.cpp` supports grammars to constrain model output. For example, you can force the model to output JSON only:
```bash
./main-m ./models/13B/ggml-model-q4_0.gguf -n 256 --grammar-file grammars/json.gbnf -p'Request: schedule a call at 8pm; Command:'
./llama-cli-m ./models/13B/ggml-model-q4_0.gguf -n 256 --grammar-file grammars/json.gbnf -p'Request: schedule a call at 8pm; Command:'
```
The `grammars/` folder contains a handful of sample grammars. To write your own, check out the [GBNF Guide](./grammars/README.md).
For authoring more complex JSON grammars, you can also check out https://grammar.intrinsiclabs.ai/, a browser app that lets you write TypeScript interfaces which it compiles to GBNF grammars that you can save for local use. Note that the app is built and maintained by members of the community, please file any issues or FRs on [its repo](http://github.com/intrinsiclabsai/gbnfgen) and not this one.
### Instruct mode
1. First, download and place the `ggml` model into the `./models` folder
2. Run the `main` tool like this:
```
./examples/alpaca.sh
```
Sample run:
```
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to LLaMA.
- If you want to submit another line, end your input in '\'.
Below is an instruction that describes a task. Write a response that appropriately completes the request.
> How many letters are there in the English alphabet?
There 26 letters in the English Alphabet
> What is the most common way of transportation in Amsterdam?
The majority (54%) are using public transit. This includes buses, trams and metros with over 100 lines throughout the city which make it very accessible for tourists to navigate around town as well as locals who commute by tram or metro on a daily basis
> List 5 words that start with "ca".
cadaver, cauliflower, cabbage (vegetable), catalpa (tree) and Cailleach.
>
```
### Obtaining and using the Facebook LLaMA 2 model
- Refer to [Facebook's LLaMA download page](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) if you want to access the model data.
- Alternatively, if you want to save time and space, you can download already converted and quantized models from [TheBloke](https://huggingface.co/TheBloke), including:
If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:
- LLaMA:
-[Introducing LLaMA: A foundational, 65-billion-parameter large language model](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/)
-[LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
- GPT-3
-[Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165)
- GPT-3.5 / InstructGPT / ChatGPT:
-[Aligning language models to follow instructions](https://openai.com/research/instruction-following)
-[Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
### Android
#### Build on Android using Termux
[Termux](https://github.com/termux/termux-app#installation) is a method to execute `llama.cpp` on an Android device (no root required).
```
apt update && apt upgrade -y
apt install git make cmake
```
It's recommended to move your model inside the `~/` directory for best performance:
```
cd storage/downloads
mv model.gguf ~/
```
[Get the code](https://github.com/ggerganov/llama.cpp#get-the-code) & [follow the Linux build instructions](https://github.com/ggerganov/llama.cpp#build) to build `llama.cpp`.
#### Building the Project using Android NDK
Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice).
Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission:
(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
Download model [llama-2-7b-chat.Q4_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf), and push it to `/sdcard/llama.cpp/`, then move it to `/data/data/com.termux/files/home/model/`
* Docker must be installed and running on your system.
* Create a folder to store big models & intermediate files (ex. /llama/models)
#### Images
We have three Docker images available for this project:
## Build
1.`ghcr.io/ggerganov/llama.cpp:full`: This image includes both the main executable file and the tools to convert LLaMA models into ggml and convert into 4-bit quantization. (platforms: `linux/amd64`, `linux/arm64`)
2.`ghcr.io/ggerganov/llama.cpp:light`: This image only includes the main executable file. (platforms: `linux/amd64`, `linux/arm64`)
3.`ghcr.io/ggerganov/llama.cpp:server`: This image only includes the server executable file. (platforms: `linux/amd64`, `linux/arm64`)
Please refer to [Build llama.cpp locally](./docs/build.md)
Additionally, there the following images, similar to the above:
## Supported backends
-`ghcr.io/ggerganov/llama.cpp:full-cuda`: Same as `full` but compiled with CUDA support. (platforms: `linux/amd64`)
-`ghcr.io/ggerganov/llama.cpp:light-cuda`: Same as `light` but compiled with CUDA support. (platforms: `linux/amd64`)
-`ghcr.io/ggerganov/llama.cpp:server-cuda`: Same as `server` but compiled with CUDA support. (platforms: `linux/amd64`)
-`ghcr.io/ggerganov/llama.cpp:full-rocm`: Same as `full` but compiled with ROCm support. (platforms: `linux/amd64`, `linux/arm64`)
-`ghcr.io/ggerganov/llama.cpp:light-rocm`: Same as `light` but compiled with ROCm support. (platforms: `linux/amd64`, `linux/arm64`)
-`ghcr.io/ggerganov/llama.cpp:server-rocm`: Same as `server` but compiled with ROCm support. (platforms: `linux/amd64`, `linux/arm64`)
| Backend | Target devices |
| --- | --- |
| [Metal](./docs/build.md#metal-build) | Apple Silicon |
| [BLAS](./docs/build.md#blas-build) | All |
| [BLIS](./docs/backend/BLIS.md) | All |
| [SYCL](./docs/backend/SYCL.md) | Intel and Nvidia GPU |
| [MUSA](./docs/build.md#musa) | Moore Threads GPU |
| [CUDA](./docs/build.md#cuda) | Nvidia GPU |
| [hipBLAS](./docs/build.md#hipblas) | AMD GPU |
| [Vulkan](./docs/build.md#vulkan) | GPU |
The GPU enabled images are not currently tested by CI beyond being built. They are not built with any variation from the ones in the Dockerfiles defined in [.devops/](.devops/) and the GitHub Action defined in [.github/workflows/docker.yml](.github/workflows/docker.yml). If you need different settings (for example, a different CUDA or ROCm library, you'll need to build the images locally for now).
## Tools
#### Usage
The easiest way to download the models, convert them to ggml and optimize them is with the --all-in-one command which includes the full docker image.
Replace `/path/to/models` below with the actual path where you downloaded the models.
```bash
docker run -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:full --all-in-one"/models/" 7B
```
On completion, you are ready to play!
```bash
docker run -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:full --run-m /models/7B/ggml-model-q4_0.gguf -p"Building a website can be done in 10 simple steps:"-n 512
```
or with a light image:
```bash
docker run -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:light -m /models/7B/ggml-model-q4_0.gguf -p"Building a website can be done in 10 simple steps:"-n 512
Assuming one has the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit) properly installed on Linux, or is using a GPU enabled cloud, `cuBLAS` should be accessible inside the container.
You may want to pass in some different `ARGS`, depending on the CUDA environment supported by your container host, as well as the GPU architecture.
### Prepare and Quantize
The defaults are:
> [!NOTE]
> You can use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space on Hugging Face to quantise your model weights without any setup too. It is synced from `llama.cpp` main every 6 hours.
-`CUDA_VERSION` set to `11.7.1`
-`CUDA_DOCKER_ARCH` set to `all`
To obtain the official LLaMA 2 weights please see the <ahref="#obtaining-and-using-the-facebook-llama-2-model">Obtaining and using the Facebook LLaMA 2 model</a> section. There is also a large selection of pre-quantized `gguf` models available on Hugging Face.
The resulting images, are essentially the same as the non-CUDA images:
Note: `convert.py` has been moved to `examples/convert_legacy_llama.py` and shouldn't be used for anything other than `Llama/Llama2/Mistral` models and their derivatives.
It does not support LLaMA 3, you can use `convert_hf_to_gguf.py` with LLaMA 3 downloaded from Hugging Face.
1.`local/llama.cpp:full-cuda`: This image includes both the main executable file and the tools to convert LLaMA models into ggml and convert into 4-bit quantization.
2.`local/llama.cpp:light-cuda`: This image only includes the main executable file.
3.`local/llama.cpp:server-cuda`: This image only includes the server executable file.
To learn more about quantizing model, [read this documentation](./examples/quantize/README.md)
#### Usage
### Perplexity (measuring model quality)
After building locally, Usage is similar to the non-CUDA examples, but you'll need to add the `--gpus` flag. You will also want to use the `--n-gpu-layers` flag.
You can use the `perplexity` example to measure perplexity over a given prompt (lower perplexity is better).
For more information, see [https://huggingface.co/docs/transformers/perplexity](https://huggingface.co/docs/transformers/perplexity).
```bash
docker run --gpus all -v /path/to/models:/models local/llama.cpp:full-cuda --run-m /models/7B/ggml-model-q4_0.gguf -p"Building a website can be done in 10 simple steps:"-n 512 --n-gpu-layers 1
docker run --gpus all -v /path/to/models:/models local/llama.cpp:light-cuda -m /models/7B/ggml-model-q4_0.gguf -p"Building a website can be done in 10 simple steps:"-n 512 --n-gpu-layers 1
docker run --gpus all -v /path/to/models:/models local/llama.cpp:server-cuda -m /models/7B/ggml-model-q4_0.gguf --port 8000 --host 0.0.0.0 -n 512 --n-gpu-layers 1
```
To learn more how to measure perplexity using llama.cpp, [read this documentation](./examples/perplexity/README.md)
### Contributing
## Contributing
- Contributors can open PRs
- Collaborators can push to branches in the `llama.cpp` repo and merge PRs into the `master` branch
- Collaborators will be invited based on contributions
- Any help with managing issues and PRs is very appreciated!
- See [good first issues](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) for tasks suitable for first contributions
- Read the [CONTRIBUTING.md](CONTRIBUTING.md) for more information
- Make sure to read this: [Inference at the edge](https://github.com/ggerganov/llama.cpp/discussions/205)
- A bit of backstory for those who are interested: [Changelog podcast](https://changelog.com/podcast/532)
### Coding guidelines
## Other documentations
- Avoid adding third-party dependencies, extra files, extra headers, etc.
- Always consider cross-compatibility with other operating systems and architectures
- Avoid fancy looking modern STL constructs, use basic `for` loops, avoid templates, keep it simple
- There are no strict rules for the code style, but try to follow the patterns in the code (indentation, spaces, etc.). Vertical alignment makes things more readable and easier to batch edit
- Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line, `void * ptr`, `int & a`
- See [good first issues](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) for tasks suitable for first contributions
- Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices
- Matrix multiplication is unconventional: [`C = ggml_mul_mat(ctx, A, B)`](https://github.com/ggerganov/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064) means $C^T = A B^T \Leftrightarrow C = B A^T.$
If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:
- LLaMA:
-[Introducing LLaMA: A foundational, 65-billion-parameter large language model](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/)
-[LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
- GPT-3
-[Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165)
- GPT-3.5 / InstructGPT / ChatGPT:
-[Aligning language models to follow instructions](https://openai.com/research/instruction-following)
-[Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
(time ./bin/llama-cli--model${model_f16}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-f16.log
(time ./bin/llama-cli--model${model_q8_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q8_0.log
(time ./bin/llama-cli--model${model_q4_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_0.log
(time ./bin/llama-cli--model${model_q4_1}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_1.log
(time ./bin/llama-cli--model${model_q5_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_0.log
(time ./bin/llama-cli--model${model_q5_1}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_1.log
(time ./bin/llama-cli--model${model_q2_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q2_k.log
(time ./bin/llama-cli--model${model_q3_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q3_k.log
(time ./bin/llama-cli--model${model_q4_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_k.log
(time ./bin/llama-cli--model${model_q5_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_k.log
(time ./bin/llama-cli--model${model_q6_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q6_k.log
(time ./bin/llama-cli--model${model_f16}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-f16.log
(time ./bin/llama-cli--model${model_q8_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q8_0.log
(time ./bin/llama-cli--model${model_q4_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_0.log
(time ./bin/llama-cli--model${model_q4_1}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_1.log
(time ./bin/llama-cli--model${model_q5_0}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_0.log
(time ./bin/llama-cli--model${model_q5_1}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_1.log
(time ./bin/llama-cli--model${model_q2_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q2_k.log
(time ./bin/llama-cli--model${model_q3_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q3_k.log
(time ./bin/llama-cli--model${model_q4_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q4_k.log
(time ./bin/llama-cli--model${model_q5_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q5_k.log
(time ./bin/llama-cli--model${model_q6_k}-t 1 -ngl 999 -s 1234 -n 256 --ignore-eos-p"I believe the meaning of life is") 2>&1 | tee-a$OUT/${ci}-tg-q6_k.log
