thu-ml / TetraJet-MXFP4TrainingLinks
Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training
☆29Updated 3 months ago
Alternatives and similar repositories for TetraJet-MXFP4Training
Users that are interested in TetraJet-MXFP4Training are comparing it to the libraries listed below
Sorting:
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆150Updated 4 months ago
- ☆22Updated 11 months ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆54Updated 2 months ago
- Work in progress.☆74Updated 3 months ago
- ☆142Updated 7 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆94Updated 10 months ago
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆67Updated last year
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆38Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆21Updated 7 months ago
- ☆126Updated 4 months ago
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆44Updated 3 months ago
- ☆24Updated 6 months ago
- ☆29Updated 10 months ago
- ☆29Updated last year
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆64Updated 2 months ago
- ☆46Updated 11 months ago
- LLM Inference with Microscaling Format☆31Updated 10 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 2 months ago
- AFPQ code implementation☆23Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆78Updated 11 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆44Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆189Updated 3 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆115Updated 3 months ago
- The evaluation framework for training-free sparse attention in LLMs☆98Updated 3 months ago
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆59Updated 6 months ago
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆51Updated last month