QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
☆162Aug 21, 2025Updated last year
Alternatives and similar repositories for QQQ
Users that are interested in QQQ are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆870Mar 6, 2025Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆178Nov 26, 2025Updated 11 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,181Sep 4, 2024Updated 2 years ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆102Sep 4, 2024Updated 2 years ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆112Apr 7, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [COLM 2025] DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation; 知乎:https://zhuanlan.zhihu.c…☆30Mar 5, 2025Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆230Nov 25, 2025Updated 11 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆543Nov 26, 2024Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆351Jul 2, 2024Updated 2 years ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆100Jul 28, 2025Updated last year
- Model Compression Toolbox for Large Language Models and Diffusion Models☆804Aug 14, 2025Updated last year
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆249Sep 30, 2024Updated 2 years ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆444Feb 14, 2025Updated last year
- Pytorch implementation of our paper OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks accepted by ECCV 2024.☆18Jul 6, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆190Apr 24, 2026Updated 6 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆397Apr 13, 2025Updated last year
- ☆92Jan 23, 2025Updated last year
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆137Oct 15, 2025Updated last year
- ☆210May 5, 2025Updated last year
- Benchmarking code for running quantized kernels from vLLM and other libraries☆14Dec 3, 2024Updated last year
- ☆200Jun 22, 2025Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆282Jul 16, 2025Updated last year
- Pytorch implementation of our paper SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration accepted by NeurIPS …☆22Mar 12, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A quantization algorithm for LLM☆154Jun 21, 2024Updated 2 years ago
- ☆26Oct 31, 2024Updated 2 years ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆772Aug 6, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆493Oct 1, 2026Updated last month
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆359Mar 10, 2026Updated 8 months ago
- Pytorch implementation of our paper MaxQ: Multi-Axis Query for N:M Sparsity Network accepted by CVPR 2024.☆37Mar 12, 2024Updated 2 years ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆137Nov 4, 2026Updated 2 weeks ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆123Mar 6, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆59Nov 5, 2024Updated 2 years ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆227Dec 15, 2023Updated 2 years ago
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascen…☆1,295Updated this week
- ☆156Mar 4, 2025Updated last year
- Code for data-aware compression of DeepSeek models☆75Dec 11, 2025Updated 11 months ago
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆52Oct 21, 2023Updated 3 years ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆440Aug 13, 2024Updated 2 years ago
Are these results useful?