BrotherHappy / OSTQuant
[ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
☆43Updated 2 weeks ago
Alternatives and similar repositories for OSTQuant:
Users that are interested in OSTQuant are comparing it to the libraries listed below
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆127Updated 2 months ago
- Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆120Updated 3 weeks ago
- ☆20Updated 5 months ago
- Code Repository of Evaluating Quantized Large Language Models☆121Updated 7 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆60Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆47Updated 2 years ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆49Updated last year
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆47Updated last year
- Official implementation of the ICLR 2024 paper AffineQuant☆25Updated last year
- AFPQ code implementation☆20Updated last year
- LLM Inference with Microscaling Format☆20Updated 5 months ago
- ☆68Updated 3 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆115Updated 2 weeks ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆156Updated 6 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆174Updated 10 months ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆33Updated 6 months ago
- ☆54Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆104Updated this week
- This repository contains integer operators on GPUs for PyTorch.☆202Updated last year
- Code implementation of GPTQv2 (https://arxiv.org/abs/2504.02692)☆29Updated this week
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆29Updated 8 months ago
- 16-fold memory access reduction with nearly no loss☆90Updated 3 weeks ago
- ☆40Updated 9 months ago
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆49Updated 3 weeks ago
- A sparse attention kernel supporting mix sparse patterns☆192Updated 2 months ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆118Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆63Updated 6 months ago
- ☆24Updated 5 months ago
- This is a repository of Binary General Matrix Multiply (BGEMM) by customized CUDA kernel. Thank FP6-LLM for the wheels!☆14Updated 7 months ago