The official implementation of the DAC 2024 paper GQA-LUT
☆20Dec 20, 2024Updated last year
Alternatives and similar repositories for GQA-LUT
Users that are interested in GQA-LUT are comparing it to the libraries listed below
Sorting:
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆38Sep 24, 2024Updated last year
- The official implementation of the ICML 2023 paper OFQ-ViT☆39Oct 3, 2023Updated 2 years ago
- Residual vector quantization for KV cache compression in large language model☆11Oct 22, 2024Updated last year
- [TMLR] Official PyTorch implementation of paper "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precisio…☆48Sep 27, 2024Updated last year
- ☆10Oct 28, 2024Updated last year
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆37Aug 20, 2024Updated last year
- ☆15Apr 2, 2025Updated 11 months ago
- ☆19Oct 2, 2024Updated last year
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆30Dec 6, 2023Updated 2 years ago
- ☆17Jul 24, 2023Updated 2 years ago
- Work in progress.☆79Nov 25, 2025Updated 3 months ago
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆20Jan 24, 2025Updated last year
- ☆16Nov 14, 2022Updated 3 years ago
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆18Dec 13, 2024Updated last year
- ☆22Feb 29, 2024Updated 2 years ago
- Fast and low-memory attention layer written in CUDA☆20Jul 14, 2023Updated 2 years ago
- This repo contains the code for studying the interplay between quantization and sparsity methods☆26Feb 26, 2025Updated last year
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆73Mar 25, 2025Updated 11 months ago
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- [CoLM 24] Official Repository of MambaByte: Token-free Selective State Space Model☆24Oct 12, 2024Updated last year
- [ICLR 2026] SparseD: Sparse Attention for Diffusion Language Models☆59Feb 22, 2026Updated last week
- Compressing Large Language Models using Low Precision and Low Rank Decomposition☆106Nov 24, 2025Updated 3 months ago
- [CVPR 2025] VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?☆29May 10, 2025Updated 9 months ago
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆27Jun 25, 2024Updated last year
- ☆235Jun 11, 2024Updated last year
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆282Aug 28, 2025Updated 6 months ago
- [CVPR 2024 Highlight] GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding☆27Jul 26, 2024Updated last year
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆31Mar 7, 2024Updated 2 years ago
- Official Pytorch implementations for "Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation"(EC…☆33Mar 15, 2025Updated 11 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆133May 16, 2024Updated last year
- Codebase for fine-tuning Llama2 70B to generate math test questions and answers.☆11Aug 30, 2024Updated last year
- [HPCA 2023] ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design☆128Jun 27, 2023Updated 2 years ago
- ☆46Sep 27, 2025Updated 5 months ago
- XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts☆35Jul 2, 2024Updated last year
- ☆42Mar 28, 2024Updated last year
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆30Mar 14, 2024Updated last year
- xKV: Cross-Layer SVD for KV-Cache Compression☆45Nov 30, 2025Updated 3 months ago
- ☆82Apr 1, 2024Updated last year