LLM KV Cache compression - K+V dual compression, 73-99% VRAM savings, zero accuracy loss
☆57Mar 30, 2026Updated 5 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:
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated last month
- ☆122May 16, 2025Updated last year
- ☆21Mar 22, 2021Updated 5 years ago
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆99May 14, 2026Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆13Jul 24, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆49Apr 15, 2024Updated 2 years 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
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated last year
- Super fast accurate face detector ! SCRFD(CVPR 2021) with MNN/TNN/NCNN/ONNXRuntime C++.☆21Jan 12, 2022Updated 4 years ago
- Cute layout visualization☆45Jan 18, 2026Updated 7 months ago
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 6 months ago
- Distilling Knowledge via Intermediate Classifiers☆16Oct 3, 2021Updated 4 years ago
- PyTorch implementation of Language model compression with weighted low-rank factorization☆14Jun 28, 2023Updated 3 years ago
- ☆18Sep 23, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- LLM Inference FrameWork☆36May 20, 2026Updated 3 months ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 4 months ago
- Fully open reproduction of DeepSeek-R1☆11Mar 24, 2025Updated last year
- 集中管理所有的prompt。☆14Nov 27, 2024Updated last year
- ☆21Apr 27, 2026Updated 4 months ago
- ☆32Jul 2, 2025Updated last year
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 4 months ago
- Official implementation for LaCo (EMNLP 2024 Findings)☆22Oct 3, 2024Updated last year
- A skill for automatically optimizing CUDA code.☆43Mar 26, 2026Updated 5 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.
- Dirve human model in Unity through 3D keypoints☆11Sep 30, 2019Updated 6 years ago
- VSS: A Storage System for Video Analytics☆13Jul 9, 2021Updated 5 years ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆16Nov 11, 2024Updated last year
- KFunca: A minimalist, high-performance GPU-based automatic differentiation framework☆31Aug 14, 2025Updated last year
- Based on TensorRT v8.2, build network for YOLOv5-v5.0 by myself, speed up YOLOv5-v5.0 inferencing☆14Oct 18, 2025Updated 10 months ago
- Some funny cute/cuteDSL code snippets☆34Mar 2, 2026Updated 5 months ago
- A tutorial for CUDA&PyTorch☆508Mar 23, 2026Updated 5 months ago
- 🍎 One kernel a day keeps high latency away. A hands-on CUDA learning path featuring a rich collection of kernels, from the basics to pea…☆212Updated this week
- my solution for UC Berkeley AI projects pacman☆11Jul 25, 2020Updated 6 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A rust-version of NVIDIA BlueField DOCA kit.☆13Jun 11, 2023Updated 3 years ago
- Inference Llama 2 in one file of pure Cuda☆17Aug 20, 2023Updated 3 years ago
- 分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等☆3,727Aug 7, 2026Updated 3 weeks ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Kimi K2 Thinking Agentic Search Unofficial Implementation☆15Nov 9, 2025Updated 9 months ago
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆243Jul 18, 2025Updated last year
- A system for scheduling serverless edge functions☆11Aug 11, 2020Updated 6 years ago