a minimal cache manager for PagedAttention, on top of llama3.
☆146Aug 26, 2024Updated last year
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:
- Mixed precision training from scratch with Tensors and CUDA☆30May 14, 2024Updated 2 years ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,166Dec 30, 2024Updated last year
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy☆62Jun 18, 2026Updated 3 weeks ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆47Jun 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.
- ☆48Nov 1, 2025Updated 8 months ago
- A minimal implementation of vllm.☆73Jul 27, 2024Updated last year
- Fastest kernels written from scratch☆583Sep 18, 2025Updated 9 months ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆13Nov 23, 2024Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆299Jun 24, 2026Updated 2 weeks ago
- Applied AI experiments and examples for PyTorch☆322Aug 22, 2025Updated 10 months ago
- ☆15Mar 30, 2024Updated 2 years ago
- ☆52May 19, 2025Updated last year
- ☆10Feb 20, 2024Updated 2 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.
- Explore training for quantized models☆26Jul 12, 2025Updated 11 months ago
- Cataloging released Triton kernels.☆310Sep 9, 2025Updated 10 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆500Jun 10, 2026Updated last month
- Framework to reduce autotune overhead to zero for well known deployments.☆101Sep 19, 2025Updated 9 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆31Jul 1, 2026Updated last week
- ☆27Jan 8, 2024Updated 2 years ago
- ☆18Sep 22, 2024Updated last year
- A lightweight design for computation-communication overlap.☆240Jan 20, 2026Updated 5 months ago
- ☆91Jan 23, 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.
- Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code☆10Aug 29, 2023Updated 2 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆193Feb 11, 2026Updated 4 months ago
- Parsers for CUDA binary files☆25Dec 29, 2023Updated 2 years ago
- ☆146Aug 18, 2025Updated 10 months ago
- Implementation of FlashAttention (FA1-FA4) in PyTorch for educational and algorithmic clarity☆223Apr 12, 2026Updated 2 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆75Sep 8, 2024Updated last year
- ☆250Nov 24, 2025Updated 7 months ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆442Mar 5, 2026Updated 4 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.
- Fast low-bit matmul kernels in Triton☆475Jun 30, 2026Updated last week
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- Code snippets and reproductions from JustAByte☆48Apr 6, 2026Updated 3 months ago
- The code based on vLLM for the paper “ Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention”.☆11Sep 19, 2024Updated last year
- 🎉My Collections of CUDA Kernels~☆11Jun 25, 2024Updated 2 years ago
- Implement Flash Attention using Cute.☆108Dec 17, 2024Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,896Updated this week