[ICML 2025] CommVQ: Commutative Vector Quantization for KV Cache Compression
☆27Sep 2, 2025Updated last year
Alternatives and similar repositories for CommVQ
Users that are interested in CommVQ are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Block-GTQ: RoPE-aware bit allocation for KV-cache quantization☆15Updated this week
- ☆18Sep 23, 2025Updated last year
- The official code implementation for paper "PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs"☆33May 24, 2025Updated last year
- ☆42Mar 28, 2024Updated 2 years ago
- This repository presents the source code for the paper "MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Qu…☆26Sep 1, 2026Updated 2 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ASPLOS'26] HILOS: A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs☆22Jan 18, 2026Updated 9 months ago
- KEEP：Official code for "KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning". A memory management system op…☆12Jul 9, 2026Updated 3 months ago
- [ICML2025] KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆32Jan 27, 2026Updated 9 months ago
- This repository contains low-bit quantization papers from 2020 to 2026 on top conference.☆230Aug 22, 2026Updated 2 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆356Mar 10, 2026Updated 7 months ago
- [MLSys 2026] Official code of SkipKV: Selectively Skip KV Generation and Storage for Efficient Inference with Large Reasoning Models.☆11Oct 26, 2026Updated last week
- ☆30Sep 11, 2026Updated last month
- ☆26Oct 31, 2024Updated 2 years ago
- ☆13Oct 22, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official implementation of STaR-KV: training-free spatio-temporal KV cache compression for efficient GUI vision-language models.☆22Oct 17, 2026Updated 2 weeks ago
- ☆34Mar 5, 2026Updated 7 months ago
- HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing☆15Sep 2, 2026Updated 2 months ago
- Repo for ECHO: Efficient KV Cache Offloading with Lossless Prefetching for Serving Native Sparse Attention LLMs (OSDI'26)☆41Jul 12, 2026Updated 3 months ago
- TransPimLib is a library for transcendental (and other hard-to-calculate) functions in general-purpose PIM systems, TransPimLib provides …☆15Apr 21, 2023Updated 3 years ago
- Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companio…☆16Jun 29, 2026Updated 4 months ago
- ☆198Jun 22, 2025Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆66Oct 9, 2025Updated last year
- Official implementation of "SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching" (COLM 2025). A novel KV cache com…☆15Sep 29, 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.
- ☆11May 24, 2025Updated last year
- ☆28Nov 5, 2021Updated 4 years ago
- [ICLR 2026] The official implementation of "PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models"☆18Feb 3, 2026Updated 8 months ago
- ☆16Jul 13, 2026Updated 3 months ago
- code for paper Accurate KV Cache Quantization with Outlier Tokens Tracing (ACL2025 Main)☆11Jul 4, 2025Updated last year
- Code for "Reinforcing Grounded Video Reasoning via Visual-Perception Prompting [ECCV 2026]"☆17Jul 30, 2026Updated 3 months ago
- Official implementation of the ICLR 2024 paper AffineQuant☆31Mar 30, 2024Updated 2 years ago
- ☆127Feb 26, 2026Updated 8 months ago
- Making 1.58-bit models simple to build and broadly accessible through low-cost, high-accuracy post-training ternary quantization.☆47Aug 18, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆16Jun 16, 2026Updated 4 months ago
- Collect LLM Quantization related papers, data, repositories☆12Aug 27, 2024Updated 2 years ago
- Robot manipulation with GPT-6-Astra: body knowledge, experience reuse, emergent skills, and sim2real transfer.☆13Sep 24, 2026Updated last month
- ☆12Mar 24, 2023Updated 3 years ago
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆137Oct 15, 2025Updated last year
- ☆17Sep 27, 2026Updated last month
- Residual vector quantization for KV cache compression in large language model☆12Oct 22, 2024Updated 2 years ago