tspeterkim / flash-attention-minimal
Flash Attention in ~100 lines of CUDA (forward pass only)
☆732Updated 2 months ago
Alternatives and similar repositories for flash-attention-minimal:
Users that are interested in flash-attention-minimal are comparing it to the libraries listed below
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆524Updated last month
- Tile primitives for speedy kernels☆2,153Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆769Updated this week
- Puzzles for learning Triton☆1,508Updated 4 months ago
- Fast CUDA matrix multiplication from scratch☆663Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆595Updated 2 weeks ago
- GPU programming related news and material links☆1,412Updated 2 months ago
- Helpful tools and examples for working with flex-attention☆689Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆771Updated 6 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆551Updated last month
- Ring attention implementation with flash attention☆711Updated 3 weeks ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆935Updated 2 weeks ago
- ☆190Updated last month
- Applied AI experiments and examples for PyTorch☆249Updated this week
- Cataloging released Triton kernels.☆204Updated 2 months ago
- Pipeline Parallelism for PyTorch☆757Updated 7 months ago
- Fastest kernels written from scratch☆191Updated 2 weeks ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆262Updated 3 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆299Updated 2 months ago
- LLM KV cache compression made easy☆440Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆766Updated 6 months ago
- Efficient LLM Inference over Long Sequences☆365Updated last month
- Fast low-bit matmul kernels in Triton☆263Updated this week
- Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O☆272Updated 2 months ago
- This repository contains the experimental PyTorch native float8 training UX☆222Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆370Updated 2 weeks ago
- What would you do with 1000 H100s...☆1,016Updated last year
- An open-source efficient deep learning framework/compiler, written in python.☆691Updated 3 weeks ago
- Microsoft Automatic Mixed Precision Library☆581Updated 5 months ago