
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
Stars: 7611

bitsandbytes enables accessible large language models via k-bit quantization for PyTorch. It provides features for reducing memory consumption for inference and training by using 8-bit optimizers, LLM.int8() for large language model inference, and QLoRA for large language model training. The library includes quantization primitives for 8-bit & 4-bit operations and 8-bit optimizers.
README:
bitsandbytes
enables accessible large language models via k-bit quantization for PyTorch. We provide three main features for dramatically reducing memory consumption for inference and training:
- 8-bit optimizers uses block-wise quantization to maintain 32-bit performance at a small fraction of the memory cost.
- LLM.int8() or 8-bit quantization enables large language model inference with only half the required memory and without any performance degradation. This method is based on vector-wise quantization to quantize most features to 8-bits and separately treating outliers with 16-bit matrix multiplication.
- QLoRA or 4-bit quantization enables large language model training with several memory-saving techniques that don't compromise performance. This method quantizes a model to 4-bits and inserts a small set of trainable low-rank adaptation (LoRA) weights to allow training.
The library includes quantization primitives for 8-bit & 4-bit operations, through bitsandbytes.nn.Linear8bitLt
and bitsandbytes.nn.Linear4bit
and 8-bit optimizers through bitsandbytes.optim
module.
bitsandbytes has the following minimum requirements for all platforms:
- Python 3.9+
-
PyTorch 2.3+
- Note: While we aim to provide wide backwards compatibility, we recommend using the latest version of PyTorch for the best experience.
Note: this table reflects the status of the current development branch. For the latest stable release, see the document in the 0.47.0 tag.
🚧 = In Development, 〰️ = Partially Supported, ✅ = Supported, ❌ = Not Supported
Platform | Accelerator | Hardware Requirements | LLM.int8() | QLoRA 4-bit | 8-bit Optimizers |
---|---|---|---|---|---|
🐧 Linux, glibc >= 2.24 | |||||
x86-64 | ◻️ CPU | AVX2 | ✅ | ✅ | ❌ |
🟩 NVIDIA GPU cuda
|
SM60+ minimum SM75+ recommended |
✅ | ✅ | ✅ | |
🟥 AMD GPU cuda
|
CDNA: gfx90a, gfx942 RDNA: gfx1100 |
✅ | 〰️ | ✅ | |
🟦 Intel GPU xpu
|
Data Center GPU Max Series Arc A-Series (Alchemist) Arc B-Series (Battlemage) |
✅ | ✅ | 〰️ | |
🟪 Intel Gaudi hpu
|
Gaudi2, Gaudi3 | ✅ | 〰️ | ❌ | |
aarch64 | ◻️ CPU | ✅ | ✅ | ❌ | |
🟩 NVIDIA GPU cuda
|
SM75+ | ✅ | ✅ | ✅ | |
🪟 Windows 11 / Windows Server 2019+ | |||||
x86-64 | ◻️ CPU | AVX2 | ✅ | ✅ | ❌ |
🟩 NVIDIA GPU cuda
|
SM60+ minimum SM75+ recommended |
✅ | ✅ | ✅ | |
🟦 Intel GPU xpu
|
Arc A-Series (Alchemist) Arc B-Series (Battlemage) |
✅ | ✅ | 〰️ | |
🍎 macOS 14+ | |||||
arm64 | ◻️ CPU | Apple M1+ | 🚧 | 🚧 | ❌ |
⬜ Metal mps
|
Apple M1+ | 🚧 | 🚧 | ❌ |
The continued maintenance and development of bitsandbytes
is made possible thanks to the generous support of our sponsors. Their contributions help ensure that we can keep improving the project and delivering valuable updates to the community.
bitsandbytes
is MIT licensed.
We thank Fabio Cannizzo for his work on FastBinarySearch which we use for CPU quantization.
If you found this library useful, please consider citing our work:
@article{dettmers2023qlora,
title={Qlora: Efficient finetuning of quantized llms},
author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
journal={arXiv preprint arXiv:2305.14314},
year={2023}
}
@article{dettmers2022llmint8,
title={LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale},
author={Dettmers, Tim and Lewis, Mike and Belkada, Younes and Zettlemoyer, Luke},
journal={arXiv preprint arXiv:2208.07339},
year={2022}
}
@article{dettmers2022optimizers,
title={8-bit Optimizers via Block-wise Quantization},
author={Dettmers, Tim and Lewis, Mike and Shleifer, Sam and Zettlemoyer, Luke},
journal={9th International Conference on Learning Representations, ICLR},
year={2022}
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for bitsandbytes
Similar Open Source Tools

bitsandbytes
bitsandbytes enables accessible large language models via k-bit quantization for PyTorch. It provides features for reducing memory consumption for inference and training by using 8-bit optimizers, LLM.int8() for large language model inference, and QLoRA for large language model training. The library includes quantization primitives for 8-bit & 4-bit operations and 8-bit optimizers.

awesome-llm-json
This repository is an awesome list dedicated to resources for using Large Language Models (LLMs) to generate JSON or other structured outputs. It includes terminology explanations, hosted and local models, Python libraries, blog articles, videos, Jupyter notebooks, and leaderboards related to LLMs and JSON generation. The repository covers various aspects such as function calling, JSON mode, guided generation, and tool usage with different providers and models.

Fast-dLLM
Fast-DLLM is a diffusion-based Large Language Model (LLM) inference acceleration framework that supports efficient inference for models like Dream and LLaDA. It offers fast inference support, multiple optimization strategies, code generation, evaluation capabilities, and an interactive chat interface. Key features include Key-Value Cache for Block-Wise Decoding, Confidence-Aware Parallel Decoding, and overall performance improvements. The project structure includes directories for Dream and LLaDA model-related code, with installation and usage instructions provided for using the LLaDA and Dream models.

LMForge-End-to-End-LLMOps-Platform-for-Multi-Model-Agents
LMForge is an end-to-end LLMOps platform designed for multi-model agents. It provides a comprehensive solution for managing and deploying large language models efficiently. The platform offers tools for training, fine-tuning, and deploying various types of language models, enabling users to streamline the development and deployment process. With LMForge, users can easily experiment with different model architectures, optimize hyperparameters, and scale their models to meet specific requirements. The platform also includes features for monitoring model performance, managing datasets, and collaborating with team members, making it a versatile tool for researchers and developers working with language models.

VLMEvalKit
VLMEvalKit is an open-source evaluation toolkit of large vision-language models (LVLMs). It enables one-command evaluation of LVLMs on various benchmarks, without the heavy workload of data preparation under multiple repositories. In VLMEvalKit, we adopt generation-based evaluation for all LVLMs, and provide the evaluation results obtained with both exact matching and LLM-based answer extraction.

raft
RAFT (Reusable Accelerated Functions and Tools) is a C++ header-only template library with an optional shared library that contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

cosmos-rl
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications. It provides a toolchain for large scale RL training workload with features like parallelism, asynchronous processing, low-precision training support, and a single-controller architecture. The system architecture includes Tensor Parallelism, Sequence Parallelism, Context Parallelism, FSDP Parallelism, and Pipeline Parallelism. It also utilizes a messaging system for coordinating policy and rollout replicas, along with dynamic NCCL Process Groups for fault-tolerant and elastic large-scale RL training.

verl
veRL is a flexible and efficient reinforcement learning training framework designed for large language models (LLMs). It allows easy extension of diverse RL algorithms, seamless integration with existing LLM infrastructures, and flexible device mapping. The framework achieves state-of-the-art throughput and efficient actor model resharding with 3D-HybridEngine. It supports popular HuggingFace models and is suitable for users working with PyTorch FSDP, Megatron-LM, and vLLM backends.

llm-hosting-container
The LLM Hosting Container repository provides Dockerfile and associated resources for building and hosting containers for large language models, specifically the HuggingFace Text Generation Inference (TGI) container. This tool allows users to easily deploy and manage large language models in a containerized environment, enabling efficient inference and deployment of language-based applications.

litgpt
LitGPT is a command-line tool designed to easily finetune, pretrain, evaluate, and deploy 20+ LLMs **on your own data**. It features highly-optimized training recipes for the world's most powerful open-source large-language-models (LLMs).

Langchain-Projects-LLM
Langchain-Projects-LLM is a repository containing various projects utilizing Large Language Models such as GPT and LLAMA from HuggingFace and OpenAI. Users need the OpenAI API to run these models.

confabulations
LLM Confabulation Leaderboard evaluates large language models based on confabulations and non-response rates to challenging questions. It includes carefully curated questions with no answers in provided texts, aiming to differentiate between various models. The benchmark combines confabulation and non-response rates for comprehensive ranking, offering insights into model performance and tendencies. Additional notes highlight the meticulous human verification process, challenges faced by LLMs in generating valid responses, and the use of temperature settings. Updates and other benchmarks are also mentioned, providing a holistic view of the evaluation landscape.

llvm-aie
This repository extends the LLVM framework to generate code for use with AMD/Xilinx AI Engine processors. AI Engine processors are in-order, exposed-pipeline VLIW processors focused on application acceleration for AI, Machine Learning, and DSP applications. The repository adds LLVM support for specific features like non-power of 2 pointers, operand latencies, resource conflicts, negative operand latencies, slot assignment, relocations, code alignment restrictions, and register allocation. It includes support for Clang, LLD, binutils, Compiler-RT, and LLVM-LIBC.

awesome-transformer-nlp
This repository contains a hand-curated list of great machine (deep) learning resources for Natural Language Processing (NLP) with a focus on Generative Pre-trained Transformer (GPT), Bidirectional Encoder Representations from Transformers (BERT), attention mechanism, Transformer architectures/networks, Chatbot, and transfer learning in NLP.

llm_recipes
This repository showcases the author's experiments with Large Language Models (LLMs) for text generation tasks. It includes dataset preparation, preprocessing, model fine-tuning using libraries such as Axolotl and HuggingFace, and model evaluation.

agentscope
AgentScope is an agent-oriented programming tool for building LLM (Large Language Model) applications. It provides transparent development, realtime steering, agentic tools management, model agnostic programming, LEGO-style agent building, multi-agent support, and high customizability. The tool supports async invocation, reasoning models, streaming returns, async/sync tool functions, user interruption, group-wise tools management, streamable transport, stateful/stateless mode MCP client, distributed and parallel evaluation, multi-agent conversation management, and fine-grained MCP control. AgentScope Studio enables tracing and visualization of agent applications. The tool is highly customizable and encourages customization at various levels.
For similar tasks

bitsandbytes
bitsandbytes enables accessible large language models via k-bit quantization for PyTorch. It provides features for reducing memory consumption for inference and training by using 8-bit optimizers, LLM.int8() for large language model inference, and QLoRA for large language model training. The library includes quantization primitives for 8-bit & 4-bit operations and 8-bit optimizers.

fsdp_qlora
The fsdp_qlora repository provides a script for training Large Language Models (LLMs) with Quantized LoRA and Fully Sharded Data Parallelism (FSDP). It integrates FSDP+QLoRA into the Axolotl platform and offers installation instructions for dependencies like llama-recipes, fastcore, and PyTorch. Users can finetune Llama-2 70B on Dual 24GB GPUs using the provided command. The script supports various training options including full params fine-tuning, LoRA fine-tuning, custom LoRA fine-tuning, quantized LoRA fine-tuning, and more. It also discusses low memory loading, mixed precision training, and comparisons to existing trainers. The repository addresses limitations and provides examples for training with different configurations, including BnB QLoRA and HQQ QLoRA. Additionally, it offers SLURM training support and instructions for adding support for a new model.

Anima
Anima is the first open-source 33B Chinese large language model based on QLoRA, supporting DPO alignment training and open-sourcing a 100k context window model. The latest update includes AirLLM, a library that enables inference of 70B LLM from a single GPU with just 4GB memory. The tool optimizes memory usage for inference, allowing large language models to run on a single 4GB GPU without the need for quantization or other compression techniques. Anima aims to democratize AI by making advanced models accessible to everyone and contributing to the historical process of AI democratization.

pgvecto.rs
pgvecto.rs is a Postgres extension written in Rust that provides vector similarity search functions. It offers ultra-low-latency, high-precision vector search capabilities, including sparse vector search and full-text search. With complete SQL support, async indexing, and easy data management, it simplifies data handling. The extension supports various data types like FP16/INT8, binary vectors, and Matryoshka embeddings. It ensures system performance with production-ready features, high availability, and resource efficiency. Security and permissions are managed through easy access control. The tool allows users to create tables with vector columns, insert vector data, and calculate distances between vectors using different operators. It also supports half-precision floating-point numbers for better performance and memory usage optimization.

TPI-LLM
TPI-LLM (Tensor Parallelism Inference for Large Language Models) is a system designed to bring LLM functions to low-resource edge devices, addressing privacy concerns by enabling LLM inference on edge devices with limited resources. It leverages multiple edge devices for inference through tensor parallelism and a sliding window memory scheduler to minimize memory usage. TPI-LLM demonstrates significant improvements in TTFT and token latency compared to other models, and plans to support infinitely large models with low token latency in the future.

KIVI
KIVI is a plug-and-play 2bit KV cache quantization algorithm optimizing memory usage by quantizing key cache per-channel and value cache per-token to 2bit. It enables LLMs to maintain quality while reducing memory usage, allowing larger batch sizes and increasing throughput in real LLM inference workloads.

pointer
Pointer is a lightweight and efficient tool for analyzing and visualizing data structures in C and C++ programs. It provides a user-friendly interface to track memory allocations, pointer references, and data structures, helping developers to identify memory leaks, pointer errors, and optimize memory usage. With Pointer, users can easily navigate through complex data structures, visualize memory layouts, and debug pointer-related issues in their codebase. The tool offers interactive features such as memory snapshots, pointer tracking, and memory visualization, making it a valuable asset for C and C++ developers working on memory-intensive applications.

llm-awq
AWQ (Activation-aware Weight Quantization) is a tool designed for efficient and accurate low-bit weight quantization (INT3/4) for Large Language Models (LLMs). It supports instruction-tuned models and multi-modal LMs, providing features such as AWQ search for accurate quantization, pre-computed AWQ model zoo for various LLMs, memory-efficient 4-bit linear in PyTorch, and efficient CUDA kernel implementation for fast inference. The tool enables users to run large models on resource-constrained edge platforms, delivering more efficient responses with LLM/VLM chatbots through 4-bit inference.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.