SAI-Lab-NYU / QSVDLinks
This repository provides the official implementation of QSVD, a method for efficient low-rank approximation that unifies Query-Key-Value (QKV) weight compression in low-precision Vision-Language Models (VLMs).
☆24Updated 2 months ago
Alternatives and similar repositories for QSVD
Users that are interested in QSVD are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆34Updated 7 months ago
- Fork of Flame repo for training of some new stuff in development☆19Updated 3 weeks ago
- Official PyTorch Implementation of "Flow Map Distillation Without Data"☆115Updated 2 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Updated last year
- Model Merging with Functional Dual Anchors☆45Updated 2 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆20Updated 7 months ago
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆17Updated 10 months ago
- ☆15Updated 2 weeks ago
- [ICLR2026] The first W4A4KV4 quantized + 50% sparse LLMs!☆21Updated this week
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆59Updated 10 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆29Updated 6 months ago
- Triton implement of bi-directional (non-causal) linear attention☆63Updated 11 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆29Updated last year
- [NeurIPS'25] The official code implementation for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Tok…☆75Updated this week
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆30Updated last year
- Work in progress.☆79Updated 2 months ago
- Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)☆31Updated last year
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆50Updated 5 months ago
- Resa: Transparent Reasoning Models via SAEs☆47Updated 4 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆29Updated 3 months ago
- Code repository for the public reproduction of the language modelling experiments on "MatFormer: Nested Transformer for Elastic Inference…☆31Updated 2 years ago
- Official implementation of ECCV24 paper: POA☆24Updated last year
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆60Updated last year
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics☆70Updated 2 weeks ago
- The official repo of continuous speculative decoding☆31Updated 10 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆98Updated last year
- ☆29Updated 2 months ago
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆129Updated 8 months ago
- ☆36Updated 10 months ago
- The official code of "PixelWorld: Towards Perceiving Everything as Pixels" [TMLR25]☆15Updated 4 months ago