wimh966 / outlier_suppression
The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
☆48Updated 2 years ago
Alternatives and similar repositories for outlier_suppression:
Users that are interested in outlier_suppression are comparing it to the libraries listed below
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆47Updated last year
- LLM Inference with Microscaling Format☆20Updated 4 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆58Updated last year
- ☆18Updated 4 months ago
- ☆52Updated 11 months ago
- AFPQ code implementation☆20Updated last year
- Code Repository of Evaluating Quantized Large Language Models☆117Updated 6 months ago
- DeiT implementation for Q-ViT☆24Updated 2 years ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆32Updated 5 months ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆113Updated last year
- The official implementation of the ICML 2023 paper OFQ-ViT☆30Updated last year
- This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.☆87Updated last year
- ☆20Updated 3 months ago
- ☆18Updated 3 years ago
- An official implement of CVPR 2023 paper - NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers☆22Updated last year
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆30Updated 7 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆105Updated 10 months ago
- A collection of research papers on efficient training of DNNs☆70Updated 2 years ago
- ☆50Updated last year
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆108Updated last month
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆55Updated last year
- ☆92Updated last year
- Code for ICML 2021 submission☆35Updated 3 years ago
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆51Updated 2 years ago
- ☆27Updated 11 months ago
- ☆12Updated 2 years ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆119Updated last month
- [TMLR] Official PyTorch implementation of paper "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precisio…☆41Updated 5 months ago