LLM KV Cache compression - K+V dual compression, 73-99% VRAM savings, zero accuracy loss
☆58Mar 30, 2026Updated 7 months ago
Alternatives and similar repositories for polarquant-kv
Users that are interested in polarquant-kv are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆123May 16, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆13Sep 29, 2026Updated last month
- ☆21Mar 22, 2021Updated 5 years ago
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated 3 months ago
- 中科大郑启龙2021年并行程序设计课程实验☆11Jan 15, 2022Updated 4 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆104Updated this week
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated last year
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- Cute layout visualization☆45Jan 18, 2026Updated 9 months ago
- A linker for partial GPU kernels.☆47Oct 28, 2026Updated last week
- This repository contains the artifacts for the MLSys 2026 paper AgenticCache.☆13Apr 22, 2026Updated 6 months ago
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆62Feb 6, 2026Updated 9 months ago
- Distilling Knowledge via Intermediate Classifiers☆16Oct 3, 2021Updated 5 years ago
- ☆18Sep 23, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- RTL code for the DPU chip designed for irregular graphs☆14May 30, 2022Updated 4 years ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 6 months ago
- 🖖 图谱式笔记系统，旨在提高个人笔记的使用率！☆11Jan 17, 2021Updated 5 years ago
- ☆17Jan 8, 2025Updated last year
- ☆32Jul 2, 2025Updated last year
- LLM Inference FrameWork☆40Oct 21, 2026Updated 2 weeks ago
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 6 months ago
- 集中管理所有的prompt。☆14Nov 27, 2024Updated last year
- CUDA MoE kernels.☆12Sep 21, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Fully open reproduction of DeepSeek-R1☆11Mar 24, 2025Updated last year
- ☆21Apr 27, 2026Updated 6 months ago
- ☆23Nov 26, 2024Updated last year
- The open-source release of "SpikeHard: Efficiency-Driven Neuromorphic Hardware for Heterogeneous Systems-on-Chip"☆12Oct 7, 2023Updated 3 years ago
- VSS: A Storage System for Video Analytics☆13Jul 9, 2021Updated 5 years ago
- Course Notes for CS61C☆19Oct 26, 2026Updated last week
- KFunca: A minimalist, high-performance GPU-based automatic differentiation framework☆31Aug 14, 2025Updated last year
- Official implementation for LaCo (EMNLP 2024 Findings)☆22Oct 3, 2024Updated 2 years ago
- 一个使用torch进行量化训练的demo☆13Aug 21, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- my solution for UC Berkeley AI projects pacman☆11Jul 25, 2020Updated 6 years ago
- This repository contains the code for the ICLR 2026 paper “DASH: Deterministic Attention Scheduling for High-Throughput Reproducible LLM …☆15Jun 23, 2026Updated 4 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆36Mar 1, 2023Updated 3 years ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 8 months ago
- A skill for automatically optimizing CUDA code.☆47Mar 26, 2026Updated 7 months ago
- Official repository of the "DiverseVAR: Diversity Has Always Been There in Your Visual Autoregressive Models"☆15Dec 2, 2025Updated 11 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year