mistral.rs

Blazingly fast LLM inference.

| Rust Documentation | Python Documentation | Discord | Matrix |

Please submit requests for new models here.

Get started fast 🚀

1. Install

2. Get models

3. Deploy with our easy to use APIs

   • Python
   • Rust
   • OpenAI compatible HTTP server

Quick examples

After following installation instructions

• Check out UQFF for prequantized models of various methods!

  • Models can be found here.

• 🦙📷 Run the Llama 3.2 Vision Model: documentation and guide here

  

  Credit

  ./mistralrs-server -i vision-plain -m lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k -a vllama
  

• 🌟📷 Run the Qwen2-VL Model: documentation and guide here

  ./mistralrs-server -i vision-plain -m Qwen/Qwen2-VL-2B-Instruct -a qwen2vl
  

• 🔥🧠 AnyMoE: Build a memory-efficient MoE model from anything, in seconds

  ./mistralrs-server -i toml -f toml-selectors/anymoe_lora.toml
  

• φ³ Run the new Phi 3.5/3.1/3 model with 128K context window

  ./mistralrs-server -i plain -m microsoft/Phi-3.5-mini-instruct -a phi3
  

• 🌀 Run the Phi 3.5 MoE model with 128K context window: documentation and guide here

  ./mistralrs-server -i plain -m microsoft/Phi-3.5-MoE-instruct -a phi3.5moe
  

• φ³ 📷 Run the Phi 3 vision model: documentation and guide here

  ./mistralrs-server --port 1234 vision-plain -m microsoft/Phi-3.5-vision-instruct -a phi3v
  

• 🌲📷 Run the FLUX.1 diffusion model: documentation and guide here

  

  ./mistralrs-server --port 1234 diffusion-plain -m black-forest-labs/FLUX.1-schnell -a flux
  

• Other models: see a support matrix and how to run them

Mistral.rs supports several model categories:

• Text to Text
• Text+Image to Text: Vision (see the docs)
• Text to Image: Image Generation (see the docs)

Description

Easy:

• Lightweight OpenAI API compatible HTTP server
• Python API
• Grammar support with Regex and Yacc
• ISQ (In situ quantization): run .safetensors models directly from 🤗 Hugging Face by quantizing in-place

Fast:

• Apple silicon support: ARM NEON, Accelerate, Metal
• Accelerated CPU inference with MKL, AVX support
• CUDA support with flash attention and cuDNN.
• Device mapping: load and run some layers on the device and the rest on the CPU.

Quantization:

• Details
• GGML: 2-bit, 3-bit, 4-bit, 5-bit, 6-bit and 8-bit, with ISQ support.
• GPTQ: 2-bit, 3-bit, 4-bit and 8-bit, with Marlin kernel support in 4-bit and 8-bit.
• HQQ: 4-bit and 8 bit, with ISQ support

Powerful:

• LoRA support with weight merging
• First X-LoRA inference platform with first class support
• AnyMoE: Build a memory-efficient MoE model from anything, in seconds
• Various sampling and penalty methods
• Tool calling: docs
• Prompt chunking: process large prompts in a more manageable way

Advanced features:

• PagedAttention and continuous batching
• Prefix caching
• Topology: Configure ISQ and device mapping easily
• UQFF: Quantized file format for easy mixing of quants, collection here.
• Speculative Decoding: Mix supported models as the draft model or the target model
• Dynamic LoRA adapter activation with adapter preloading: examples and docs

Documentation for mistral.rs can be found here.

This is a demo of interactive mode with streaming running Phi 3 128k mini with quantization via ISQ to Q4K.

phi3_isq_demo.mp4

Support matrix

Note: See supported models for more information

Model	Supports quantization	Supports adapters	Supports device mapping	Supported by AnyMoE
Mistral v0.1/v0.2/v0.3	✅	✅	✅	✅
Gemma	✅	✅	✅	✅
Llama 3.1/3.2	✅	✅	✅	✅
Mixtral	✅	✅	✅
Phi 2	✅	✅	✅	✅
Phi 3	✅	✅	✅	✅
Phi 3.5 MoE	✅		✅
Qwen 2.5	✅		✅	✅
Phi 3 Vision	✅		✅	✅
Idefics 2	✅		✅	✅
Gemma 2	✅	✅	✅	✅
Starcoder 2	✅	✅	✅	✅
LLaVa Next	✅		✅	✅
LLaVa	✅		✅	✅
Llama 3.2 Vision	✅		✅
Qwen2-VL	✅		✅

APIs and Integrations

Rust Crate

Rust multithreaded/async API for easy integration into any application.

• Docs
• Examples
• To install: Add mistralrs = { git = "https://github.com/EricLBuehler/mistral.rs.git" }

Python API

Python API for mistral.rs.

• Installation including PyPI
• Docs
• Examples
• Cookbook

HTTP Server

OpenAI API compatible API server

• API Docs.
• Running
• Example

Llama Index integration (Python)

• Docs: https://docs.llamaindex.ai/en/stable/examples/llm/mistral_rs/

---

Supported accelerators

• CUDA:
  • Compile with the cuda feature: --features cuda
  • FlashAttention support: compile with the flash-attn feature
  • cuDNN support: compile with thecudnn feature: --features cudnn
• Metal:
  • Compile with the metal feature: --features metal
• CPU:
  • Intel MKL: compile with the mkl feature: --features mkl
  • Apple Accelerate: compile with the accelerate feature: --features accelerate
  • ARM NEON and AVX are used automatically

Enabling features is done by passing --features ... to the build system. When using cargo run or maturin develop, pass the --features flag before the -- separating build flags from runtime flags.

• To enable a single feature like metal: cargo build --release --features metal.
• To enable multiple features, specify them in quotes: cargo build --release --features "cuda flash-attn cudnn".

Installation and Build

Note: You can use our Docker containers here. Learn more about running Docker containers: https://docs.docker.com/engine/reference/run/

Note: You can use pre-built mistralrs-server binaries here

• Install the Python package here.
• The Python package has wheels on PyPi!

1. Install required packages:

   • OpenSSL (Example on Ubuntu: sudo apt install libssl-dev)
   • Linux only: pkg-config (Example on Ubuntu: sudo apt install pkg-config)

2. Install Rust: https://rustup.rs/

   Example on Ubuntu:

   curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
   source $HOME/.cargo/env

3. Optional: Set HF token correctly (skip if already set or your model is not gated, or if you want to use the token_source parameters in Python or the command line.)

   • Note: you can install huggingface-cli as documented here.

   huggingface-cli login

4. Download the code:

   git clone https://github.com/EricLBuehler/mistral.rs.git
   cd mistral.rs

5. Build or install:

   • Base build command

     cargo build --release

   • Build with CUDA support

     cargo build --release --features cuda

   • Build with CUDA and Flash Attention V2 support

     cargo build --release --features "cuda flash-attn"

   • Build with Metal support

     cargo build --release --features metal

   • Build with Accelerate support

     cargo build --release --features accelerate

   • Build with MKL support

     cargo build --release --features mkl

   • Install with cargo install for easy command line usage

     Pass the same values to --features as you would for cargo build

     cargo install --path mistralrs-server --features cuda

6. The build process will output a binary mistralrs-server at ./target/release/mistralrs-server which may be copied into the working directory with the following command:

   Example on Ubuntu:

   cp ./target/release/mistralrs-server ./mistralrs-server
   

7. Use our APIs and integrations:

   APIs and integrations list

Getting models

There are 2 ways to get models with mistral.rs:

• From Hugging Face Hub (easiest)
• From local files
  • Running a GGUF model
  • Specify local paths

Getting models from Hugging Face Hub

Mistral.rs can automatically download models from HF Hub. To access gated models, you should provide a token source. They may be one of:

• literal:<value>: Load from a specified literal
• env:<value>: Load from a specified environment variable
• path:<value>: Load from a specified file
• cache: default: Load from the HF token at ~/.cache/huggingface/token or equivalent.
• none: Use no HF token

This is passed in the following ways:

• Command line:

./mistralrs-server --token-source none -i plain -m microsoft/Phi-3-mini-128k-instruct -a phi3

• Python:

Here is an example of setting the token source.

If token cannot be loaded, no token will be used (i.e. effectively using none).

Loading models from local files:

You can also instruct mistral.rs to load models fully locally by modifying the *_model_id arguments or options:

./mistralrs-server --port 1234 plain -m . -a mistral

Throughout mistral.rs, any model ID argument or option may be a local path and should contain the following files for each model ID option:

• --model-id (server) or model_id (python/rust) or --tok-model-id (server) or tok_model_id (python/rust):
  • config.json
  • tokenizer_config.json
  • tokenizer.json (if not specified separately)
  • .safetensors/.bin/.pth/.pt files (defaults to .safetensors)
  • preprocessor_config.json (required for vision models).
  • processor_config.json (optional for vision models).
• --quantized-model-id (server) or quantized_model_id (python/rust):
  • Specified .gguf or .ggml file.
• --x-lora-model-id (server) or xlora_model_id (python/rust):
  • xlora_classifier.safetensors
  • xlora_config.json
  • Adapters .safetensors and adapter_config.json files in their respective directories
• --adapters-model-id (server) or adapters_model_id (python/rust):
  • Adapters .safetensors and adapter_config.json files in their respective directories

Running GGUF models

To run GGUF models, the only mandatory arguments are the quantized model ID and the quantized filename. The quantized model ID can be a HF model ID.

GGUF models contain a tokenizer. However, mistral.rs allows you to run the model with a tokenizer from a specified model, typically the official one. This means there are two options:

1. With a specified tokenizer
2. With the builtin tokenizer

With a specified tokenizer

Running with a tokenizer model ID enables you to specify the model ID to source the tokenizer from:

./mistralrs-server gguf -m bartowski/Phi-3.5-mini-instruct-GGUF -f Phi-3.5-mini-instruct-Q4_K_M.gguf -t microsoft/Phi-3.5-mini-instruct

If the specified tokenizer model ID contains a tokenizer.json, then it will be used over the GGUF tokenizer.

With the builtin tokenizer

Using the builtin tokenizer:

./mistralrs-server gguf -m bartowski/Phi-3.5-mini-instruct-GGUF -f Phi-3.5-mini-instruct-Q4_K_M.gguf

(or using a local file):

./mistralrs-server gguf -m path/to/files -f Phi-3.5-mini-instruct-Q4_K_M.gguf

There are a few more ways to configure:

Chat template:

The chat template can be automatically detected and loaded from the GGUF file if no other chat template source is specified including the tokenizer model ID.

If that does not work, you can either provide a tokenizer (recommended), or specify a custom chat template.

./mistralrs-server --chat-template <chat_template> gguf -m . -f Phi-3.5-mini-instruct-Q4_K_M.gguf

Tokenizer

The following tokenizer model types are currently supported. If you would like one to be added, please raise an issue. Otherwise, please consider using the method demonstrated in examples below, where the tokenizer is sourced from Hugging Face.

Supported GGUF tokenizer types

• llama (sentencepiece)
• gpt2 (BPE)

Run with the CLI

Mistral.rs uses subcommands to control the model type. They are generally of format <XLORA/LORA>-<QUANTIZATION>. Please run ./mistralrs-server --help to see the subcommands.

Architecture for plain models

Note: for plain models, you can specify the data type to load and run in. This must be one of f32, f16, bf16 or auto to choose based on the device. This is specified in the --dype/-d parameter after the model architecture (plain).

If you do not specify the architecture, an attempt will be made to use the model's config. If this fails, please raise an issue.

• mistral
• gemma
• mixtral
• llama
• phi2
• phi3
• phi3.5moe
• qwen2
• gemma2
• starcoder2

Architecture for vision models

Note: for vision models, you can specify the data type to load and run in. This must be one of f32, f16, bf16 or auto to choose based on the device. This is specified in the --dype/-d parameter after the model architecture (vision-plain).

• phi3v
• idefics2
• llava_next
• llava
• vllama
• qwen2vl

Supported GGUF architectures

Plain:

• llama
• phi2
• phi3
• starcoder2
• qwen2

With adapters:

• llama
• phi3

Interactive mode

You can launch interactive mode, a simple chat application running in the terminal, by passing -i:

./mistralrs-server -i plain -m microsoft/Phi-3-mini-128k-instruct -a phi3

Vision models work too:

./mistralrs-server -i vision-plain -m lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k -a vllama

And even diffusion models:

./mistralrs-server -i diffusion-plain -m black-forest-labs/FLUX.1-schnell -a flux

OpenAI HTTP server

You can an HTTP server

./mistralrs-server --port 1234 plain -m microsoft/Phi-3.5-MoE-instruct -a phi3.5moe

Structured selection with a .toml file

We provide a method to select models with a .toml file. The keys are the same as the command line, with no_kv_cache and tokenizer_json being "global" keys.

Example:

./mistralrs-server --port 1234 toml -f toml-selectors/gguf.toml

---

Benchmarks

Device	Mistral.rs Completion T/s	Llama.cpp Completion T/s	Model	Quant
A10 GPU, CUDA	86	83	mistral-7b	4_K_M
Intel Xeon 8358 CPU, AVX	11	23	mistral-7b	4_K_M
Raspberry Pi 5 (8GB), Neon	2	3	mistral-7b	2_K
A100 GPU, CUDA	131	134	mistral-7b	4_K_M
RTX 6000 GPU, CUDA	103	96	mistral-7b	4_K_M

Note: All CUDA tests for mistral.rs conducted with PagedAttention enabled, block size = 32

Please submit more benchmarks via raising an issue!

Supported models

Quantization support

Model	GGUF	GGML	ISQ
Mistral	✅		✅
Gemma			✅
Llama	✅	✅	✅
Mixtral	✅		✅
Phi 2	✅		✅
Phi 3	✅		✅
Phi 3.5 MoE			✅
Qwen 2.5			✅
Phi 3 Vision			✅
Idefics 2			✅
Gemma 2			✅
Starcoder 2		✅	✅
LLaVa Next			✅
LLaVa			✅
Llama 3.2 Vision			✅

Device mapping support

Model category	Supported
Plain	✅
GGUF	✅
GGML
Vision Plain	✅

X-LoRA and LoRA support

Model	X-LoRA	X-LoRA+GGUF	X-LoRA+GGML
Mistral	✅	✅
Gemma	✅
Llama	✅	✅	✅
Mixtral	✅	✅
Phi 2	✅
Phi 3	✅	✅
Phi 3.5 MoE
Qwen 2.5
Phi 3 Vision
Idefics 2
Gemma 2	✅
Starcoder 2	✅
LLaVa Next
LLaVa
Llama 3.2 Vision

AnyMoE support

Model	AnyMoE
Mistral 7B	✅
Gemma	✅
Llama	✅
Mixtral
Phi 2	✅
Phi 3	✅
Phi 3.5 MoE
Qwen 2.5	✅
Phi 3 Vision
Idefics 2
Gemma 2	✅
Starcoder 2	✅
LLaVa Next	✅
LLaVa	✅
Llama 3.2 Vision

Using derivative model

To use a derivative model, select the model architecture using the correct subcommand. To see what can be passed for the architecture, pass --help after the subcommand. For example, when using a different model than the default, specify the following for the following types of models:

• Plain: Model id
• Quantized: Quantized model id, quantized filename, and tokenizer id
• X-LoRA: Model id, X-LoRA ordering
• X-LoRA quantized: Quantized model id, quantized filename, tokenizer id, and X-LoRA ordering
• LoRA: Model id, LoRA ordering
• LoRA quantized: Quantized model id, quantized filename, tokenizer id, and LoRA ordering
• Vision Plain: Model id

See this section to determine if it is necessary to prepare an X-LoRA/LoRA ordering file, it is always necessary if the target modules or architecture changed, or if the adapter order changed.

It is also important to check the chat template style of the model. If the HF hub repo has a tokenizer_config.json file, it is not necessary to specify. Otherwise, templates can be found in chat_templates and should be passed before the subcommand. If the model is not instruction tuned, no chat template will be found and the APIs will only accept a prompt, no messages.

For example, when using a Zephyr model:

./mistralrs-server --port 1234 --log output.txt gguf -t HuggingFaceH4/zephyr-7b-beta -m TheBloke/zephyr-7B-beta-GGUF -f zephyr-7b-beta.Q5_0.gguf

Adapter model support: X-LoRA and LoRA

An adapter model is a model with X-LoRA or LoRA. X-LoRA support is provided by selecting the x-lora-* architecture, and LoRA support by selecting the lora-* architecture. Please find docs for adapter models here. Examples may be found here.

Chat Templates and Tokenizer

Mistral.rs will attempt to automatically load a chat template and tokenizer. This enables high flexibility across models and ensures accurate and flexible chat templating. However, this behavior can be customized. Please find detailed documentation here.

Contributing

Thank you for contributing! If you have any problems or want to contribute something, please raise an issue or pull request. If you want to add a new model, please contact us via an issue and we can coordinate how to do this.

FAQ

• Debugging with the environment variable MISTRALRS_DEBUG=1 causes the following things
  • If loading a GGUF or GGML model, this will output a file containing the names, shapes, and types of each tensor.
    • mistralrs_gguf_tensors.txt or mistralrs_ggml_tensors.txt
  • More logging.
• Setting the CUDA compiler path:
  • Set the NVCC_CCBIN environment variable during build.
• Error: recompile with -fPIE:
  • Some Linux distributions require compiling with -fPIE.
  • Set the CUDA_NVCC_FLAGS environment variable to -fPIE during build: CUDA_NVCC_FLAGS=-fPIE
• Error CUDA_ERROR_NOT_FOUND or symbol not found when using a normal or vison model:
  • For non-quantized models, you can specify the data type to load and run in. This must be one of f32, f16, bf16 or auto to choose based on the device.

Credits

This project would not be possible without the excellent work at candle. Additionally, thank you to all contributors! Contributing can range from raising an issue or suggesting a feature to adding some new functionality.

⬆️ Back to Top