Flash Attention from Scratch on CUDA Ampere
☆184Sep 1, 2025Updated 10 months ago
Alternatives and similar repositories for flash_attention_from_scratch
Users that are interested in flash_attention_from_scratch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 11 months ago
- FlashSampling: Fast and Memory-Efficient Exact Sampling (https://huggingface.co/papers/2603.15854)☆74Jun 15, 2026Updated 3 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆68Mar 25, 2025Updated last year
- Tile-based language built for AI computation across all scales☆171Jun 16, 2026Updated 3 weeks ago
- SimKO: Simple Pass@K Policy Optimization☆31Oct 24, 2025Updated 8 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.
- flash attention tutorial written in python, triton, cuda, cutlass☆527Jan 20, 2026Updated 5 months ago
- Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"☆12Jul 25, 2024Updated last year
- Low overhead tracing library and trace visualizer for pipelined CUDA kernels☆136Nov 26, 2025Updated 7 months ago
- A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It …☆187Apr 22, 2026Updated 2 months ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated last year
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 6 months ago
- Multi-GPU dynamic scheduler using PGAS style cross-GPU communication☆29Jul 23, 2023Updated 2 years ago
- Gensis is a lightweight deep learning framework written from scratch in Python, with Triton as its backend for high-performance computing…☆35Jan 15, 2026Updated 5 months ago
- ☆11Feb 15, 2022Updated 4 years ago
- 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.
- ☆40Jul 28, 2025Updated 11 months ago
- ☆65Apr 26, 2025Updated last year
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆11,461Updated this week
- ☆15Sep 25, 2025Updated 9 months ago
- Perplexity GPU Kernels☆584Nov 7, 2025Updated 8 months ago
- Material for gpu-mode lectures☆6,282Jun 15, 2026Updated 3 weeks ago
- A paper review list for computer architecture and systems research, maintained by the LEMONADE group at Peking University.☆21Jul 2, 2026Updated last week
- Automated bottleneck detection and solution orchestration☆22Feb 24, 2026Updated 4 months ago
- A tool for model sparse based on torch.fx☆13Jun 3, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Co-processor for whole genome alignment☆13Jun 6, 2020Updated 6 years ago
- A Heterogeneous GPU Platform for AI and Neural Graphics☆61Jun 22, 2026Updated 2 weeks ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆110Jul 27, 2018Updated 7 years ago
- 一个开源数学大模型项目，旨在探索大模型是否具有数学创造能力，以及大模型在前沿数学研究中的潜在能力。☆20Mar 19, 2026Updated 3 months ago
- Open ABI and FFI for Machine Learning Systems☆429Updated this week
- a simple new ISA nnISA and nnSOC nnCPU nnAs nnCc☆10Mar 15, 2020Updated 6 years ago
- MIAOW2.0 FPGA implementable design☆12Oct 18, 2017Updated 8 years ago
- 该文档是个人阅读学习蜂鸟E203源码的笔记☆14Aug 1, 2023Updated 2 years ago
- ☆71Jul 8, 2025Updated last year
- 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.
- Reading notes on Speculative Decoding papers☆38Jun 2, 2026Updated last month
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆99Jun 16, 2025Updated last year
- ☆10Mar 3, 2024Updated 2 years ago
- FlashInfer: Kernel Library for LLM Serving☆5,896Updated this week
- ☆704Jun 2, 2026Updated last month
- ☆19Jan 27, 2025Updated last year
- This repository contains a SystemVerilog implementation of a parametrized Round Robin arbiter with three instantiation options☆13Jan 28, 2024Updated 2 years ago