Accurate and fast KV cache compression with a gating mechanism
☆35Jul 27, 2026Updated 3 months ago
Alternatives and similar repositories for FastKVzip
Users that are interested in FastKVzip are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Updated this week
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆228Feb 11, 2026Updated 9 months ago
- [ICLR2025] Code and data for paper: Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasonin…☆46Mar 10, 2025Updated last year
- [ICML 2025] Official PyTorch implementation of "NegMerge: Sign-Consensual Weight Merging for Machine Unlearning"☆16Nov 25, 2025Updated 11 months ago
- Prefix Sliding for efficient test-time scaling☆28Oct 16, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ECCV 2024] Official PyTorch implementation of "HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts"☆20Nov 22, 2024Updated last year
- ☆43Jun 8, 2026Updated 5 months ago
- [NeurIPS 25] InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding☆25Jan 25, 2026Updated 9 months ago
- LLM KV cache compression made easy☆1,249Updated this week
- Official code of "MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting (ICLR 2026)"☆16Jul 9, 2026Updated 4 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆751Aug 16, 2026Updated 2 months ago
- ☆31Sep 11, 2026Updated 2 months ago
- [ECCV 2026] 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering☆21Aug 19, 2026Updated 2 months ago
- [CVPR 2025] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆19Oct 4, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- This repository provides the official PyTorch implementation of the paper "VSCD: Video-based Scene Change Detection in Unaligned Scenes …☆14Jun 23, 2026Updated 4 months ago
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- ☆15Apr 25, 2025Updated last year
- ☆23Aug 24, 2026Updated 2 months ago
- ☆42Mar 28, 2024Updated 2 years ago
- [ICLR 2026] LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation☆14Mar 16, 2026Updated 7 months ago
- Design and analyze optimal deep learning models.☆32Aug 2, 2025Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆58Apr 13, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆16Mar 28, 2026Updated 7 months ago
- ☆12Jun 2, 2026Updated 5 months ago
- ☆39Mar 17, 2025Updated last year
- KV cache compression via sparse coding☆18Oct 26, 2025Updated last year
- [EMNLP 2026] SGSD: Skill-Conditioned Gated Self-Distillation for LLM Reasoning☆14Aug 21, 2026Updated 2 months ago
- An implementation of OBC algorithm packed into a module☆10Dec 28, 2023Updated 2 years ago
- ☆11May 24, 2024Updated 2 years ago
- ☆14Aug 30, 2023Updated 3 years ago
- ☆11May 15, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Calibration-free OrbitQuant for transformer backbones, with Hugging Face integration and packed CUDA/Metal inference☆15Updated this week
- Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"☆131Oct 14, 2025Updated last year
- ☆24Mar 7, 2025Updated last year
- SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation☆12Jul 6, 2026Updated 4 months ago
- [NeurIPS 2024] Efficient Large Multi-modal Models via Visual Context Compression☆66Feb 19, 2025Updated last year
- ☆14Oct 4, 2015Updated 11 years ago
- [ECCV 2026] Video-Oasis: Rethinking Evaluation of Video Understanding☆41Oct 21, 2026Updated 3 weeks ago
Are these results useful?