a minimal cache manager for PagedAttention, on top of llama3.
☆151Aug 26, 2024Updated 2 years ago
Alternatives and similar repositories for paged-attention-minimal
Users that are interested in paged-attention-minimal are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,203Dec 30, 2024Updated last year
- Mixed precision training from scratch with Tensors and CUDA☆30May 14, 2024Updated 2 years ago
- A minimal implementation of vllm.☆73Jul 27, 2024Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Reduce kernel based on CUTLASS CuTe and TMA.☆12Sep 25, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Implement Flash Attention using Cute.☆113Dec 17, 2024Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆542Oct 22, 2026Updated 2 weeks ago
- ☆15Mar 30, 2024Updated 2 years ago
- ☆40Dec 14, 2025Updated 10 months ago
- Implementation of FlashAttention (FA1-FA4) in PyTorch for educational and algorithmic clarity☆228Apr 12, 2026Updated 6 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆48Jun 11, 2025Updated last year
- A lightweight SGLang implementation built from scratch.☆12Jul 29, 2025Updated last year
- LLM training parallelisms (DP, FSDP, TP, PP) in pure C☆29Jan 27, 2026Updated 9 months ago
- Final project for the class "Deep Learning Systems Algorithms and Implementation" from CMU, where we try to make needle work with Apple M…☆11Jan 8, 2023Updated 3 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.
- Fastest kernels written from scratch☆629Aug 15, 2026Updated 2 months ago
- CUDA SGEMM optimization note☆16Oct 31, 2023Updated 3 years ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆363Nov 2, 2025Updated last year
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- ☆48Nov 1, 2025Updated last year
- Exploring how optimizations for GEMMs work☆36Feb 28, 2026Updated 8 months ago
- Tile primitives for speedy kernels☆3,795Sep 12, 2026Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆327Updated this week
- ☆54May 19, 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.
- A practical way of learning Swizzle☆45Feb 3, 2025Updated last year
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆13Nov 23, 2024Updated last year
- ☆20Apr 26, 2026Updated 6 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,870Updated this week
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆82Aug 12, 2024Updated 2 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 8 months ago
- Fast CUDA matrix multiplication from scratch☆1,356Sep 2, 2025Updated last year
- Examples and exercises from the book Programming Massively Parallel Processors - A Hands-on Approach. David B. Kirk and Wen-mei W. Hwu (T…☆80Jan 21, 2021Updated 5 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆459Mar 5, 2026Updated 8 months ago
- 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.
- CUTLASS and CuTe Examples☆143Nov 30, 2025Updated 11 months ago
- ☆10Feb 20, 2024Updated 2 years ago
- Applied AI experiments and examples for PyTorch☆321Aug 22, 2025Updated last year
- mHC kernels implemented in CUDA☆267Mar 9, 2026Updated 7 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆101Sep 19, 2025Updated last year
- ☆171Dec 27, 2024Updated last year
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago