snu-mllab / KVzipLinks
[NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
☆111Updated this week
Alternatives and similar repositories for KVzip
Users that are interested in KVzip are comparing it to the libraries listed below
Sorting:
- ☆58Updated 4 months ago
- ☆86Updated 8 months ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated this week
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆35Updated 6 months ago
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆116Updated 11 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆89Updated 4 months ago
- ☆89Updated 11 months ago
- ☆59Updated 3 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆197Updated 4 months ago
- Work in progress.☆74Updated 3 months ago
- A repository for research on medium sized language models.☆78Updated last year
- RWKV-7: Surpassing GPT☆96Updated 10 months ago
- Esoteric Language Models☆99Updated 2 months ago
- A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size☆69Updated last month
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 4 months ago
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆48Updated 5 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 5 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆148Updated last year
- ☆75Updated 3 months ago
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆60Updated 11 months ago
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More☆34Updated 4 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆125Updated last month
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated 3 weeks ago
- ☆153Updated 3 months ago
- ☆19Updated 9 months ago
- QuIP quantization☆60Updated last year
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆32Updated last month
- ☆64Updated 6 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated 2 months ago