A SOTA quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的量化工具包
☆1,619Sep 18, 2026Updated this week
Alternatives and similar repositories for auto-round
Users that are interested in auto-round are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,795Updated this week
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,257Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,709Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆3,823Updated this week
- An innovative library for efficient LLM inference via low-bit quantization☆352Aug 30, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,172Oct 8, 2024Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆959Feb 26, 2026Updated 6 months ago
- ☆122Feb 26, 2026Updated 6 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆507Apr 17, 2026Updated 5 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆340Aug 19, 2026Updated 3 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,148Sep 4, 2024Updated 2 years ago
- PyTorch native quantization for training and inference☆2,980Updated this week
- ☆129Mar 18, 2026Updated 6 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,636Jul 17, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,140Updated this week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆533Nov 26, 2024Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆228Nov 25, 2025Updated 9 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,348May 11, 2025Updated last year
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,867Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,449Updated this week
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆192Mar 23, 2026Updated 5 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆681Aug 4, 2026Updated last month
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆943Nov 26, 2025Updated 9 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆749May 14, 2026Updated 4 months ago
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,625Mar 4, 2026Updated 6 months ago
- A pytorch quantization backend for optimum☆1,053Aug 25, 2026Updated 3 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆861Mar 6, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆485Aug 9, 2026Updated last month
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆203Sep 2, 2026Updated 2 weeks ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,862Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,070Apr 11, 2025Updated last year
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆351Apr 10, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,100Aug 18, 2026Updated last month
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆203Apr 21, 2026Updated 4 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆802Aug 14, 2025Updated last year
- Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.p…☆1,330Feb 26, 2026Updated 6 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,801Jan 17, 2026Updated 8 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆92,107Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆842Updated this week