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).
☆23Updated last month
Alternatives and similar repositories for QSVD
Users that are interested in QSVD are comparing it to the libraries listed below
Sorting:
- Fork of Flame repo for training of some new stuff in development☆19Updated this week
- Work in progress.☆76Updated last month
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆60Updated last year
- 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 9 months ago
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆34Updated 6 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆20Updated 7 months ago
- Triton implement of bi-directional (non-causal) linear attention☆60Updated 11 months ago
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆50Updated 4 months ago
- Official repository for ICML 2024 paper "MoRe Fine-Tuning with 10x Fewer Parameters"☆22Updated 2 months ago
- Model Merging with Functional Dual Anchors☆44Updated last month
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆17Updated 2 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Updated last year
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Updated 2 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…☆27Updated 5 months ago
- Official Repository for Task-Circuit Quantization☆24Updated 7 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆28Updated 2 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 8 months ago
- [NeurIPS'25] The official code implementation for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Tok…☆72Updated this week
- Official implementation of ECCV24 paper: POA☆24Updated last year
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆29Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆98Updated last year
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆53Updated 5 months ago
- Official PyTorch Implementation of "Flow Map Distillation Without Data"☆112Updated last month
- Landing repository for the paper "Predicting the Order of Upcoming Tokens Improves Language Modeling"☆41Updated 3 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆28Updated last year
- Resa: Transparent Reasoning Models via SAEs☆47Updated 3 months ago
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics☆69Updated 2 weeks ago
- Implementation of the proposed MaskBit from Bytedance AI☆83Updated last year
- Lottery Ticket Adaptation☆40Updated last year
- Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)☆30Updated last year