FlashInfer

CUDA kernel library that brings Flash-attention-style optimizations to any LLM serving stack.

Visit Website

Introduction

Overview

FlashInfer provides Triton/Torch-CUDA kernels for grouped-query and sliding window attention with 2-3× speed-ups.

Key Capabilities

Drop-in Python bindings
Dynamic rope scaling & int4 support
Benchmarks on A100/H100 & RTX GPUs

Back

Information

Websiteflashinfer.ai
AuthorsFlashInfer Team
Published date2023/11/12

More Items

Ray

2017

RISELab (UC Berkeley), Anyscale Inc.

Ray is an open-source distributed compute engine that lets you scale Python and AI workloads—from data processing to model training and serving—without deep distributed-systems expertise.

ai-development ai-framework ai-train ai-serving

OpenVINO

2018

Intel

OpenVINO is an open-source toolkit from Intel that streamlines the optimization and deployment of AI inference models across a wide range of Intel® hardware.

ai-development ai-inference ai-serving

NVIDIA Dynamo

2025

NVIDIA

NVIDIA Dynamo is an open-source, high-throughput, low-latency inference framework that scales generative-AI and reasoning models across large, multi-node GPU clusters.

ai-development ai-inference ai-serving nvidia