[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
☆50Aug 7, 2025Updated last year
Alternatives and similar repositories for RocketKV
Users that are interested in RocketKV 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 comprehensive AI & ML project portfolio from the University of Texas at Austin PG Program, demonstrating real-world data science and ma…☆17Jan 25, 2026Updated 6 months ago
- [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning☆25Dec 5, 2025Updated 8 months ago
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15May 19, 2026Updated 2 months ago
- 🔥 [ICML'26] ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs☆30Updated this week
- ☆20May 30, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [NeurIPS 2025] Official PyTorch implementation of paper "Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression".☆16Oct 24, 2025Updated 9 months ago
- To appear in the 11th International Conference on Learning Representations (ICLR 2023).☆18Feb 24, 2023Updated 3 years ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆150Jul 30, 2026Updated 2 weeks ago
- Open-source of MSD framework☆16Sep 12, 2023Updated 2 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆36Jun 29, 2023Updated 3 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆311May 1, 2025Updated last year
- Algorithms for approximate attention in LLMs☆22Apr 14, 2025Updated last year
- Implementation of "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm"☆18Apr 11, 2025Updated last year
- 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.
- MathLib DAC 2023 version☆13Sep 11, 2023Updated 2 years ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆139Nov 26, 2025Updated 8 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Oct 5, 2024Updated last year
- ☆39Mar 17, 2025Updated last year
- ☆23Jun 1, 2025Updated last year
- Performs a faster tensor train (TT) decomposition for large sparse data☆14Sep 7, 2020Updated 5 years ago
- A unified VLA post-training framework for human-in-the-loop data collection, fine-tuning, and reinforcement learning.☆52Updated this week
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆108Jul 8, 2026Updated last month
- 为HSNW源码加上了详细的注释☆20Oct 26, 2022Updated 3 years ago
- 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.
- A skill for automatically optimizing CUDA code.☆43Mar 26, 2026Updated 4 months ago
- ☆31Mar 9, 2026Updated 5 months ago
- [ICLR2025] Code and data for paper: Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasonin…☆45Mar 10, 2025Updated last year
- ☆26Jan 16, 2025Updated last year
- Code for ICML 2022 paper "SPDY: Accurate Pruning with Speedup Guarantees"☆20May 3, 2023Updated 3 years ago
- The official code implementation for paper "PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs"☆29May 24, 2025Updated last year
- ☆37Jul 27, 2026Updated 2 weeks ago
- [PACT'24] GraNNDis. A fast and unified distributed graph neural network (GNN) training framework for both full-batch (full-graph) and min…☆10Aug 13, 2024Updated 2 years ago
- Official Implementation for [ICLR26] DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference☆56Mar 28, 2026Updated 4 months 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.
- Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"☆14Jun 7, 2023Updated 3 years ago
- [EMNLP 24] Source code for paper 'AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tu…☆13Dec 15, 2024Updated last year
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- Incubating P/D sidecar for llm-d☆17Nov 13, 2025Updated 9 months ago
- xKV: Cross-Layer SVD for KV-Cache Compression [ICML 2026]☆57Jul 7, 2026Updated last month
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆28May 12, 2026Updated 3 months ago
- ☆11Aug 2, 2024Updated 2 years ago