High-Performance GPU Kernels for Inference
|
Documentation
|
Latest Release
|
Blog
|
Slack
|
Discussion Forum
|
FlashInfer
is a library and kernel generator for inference that delivers state-of-the-art performance across diverse GPU architectures. It provides unified APIs for attention, GEMM, and MoE operations with multiple backend implementations including FlashAttention-2/3, cuDNN, CUTLASS, and TensorRT-LLM.
Why FlashInfer?
State-of-the-art Performance
: Optimized kernels for prefill, decode, and mixed batching scenarios
Multiple Backends
: Automatically selects the best backend for your hardware and workload
Modern Architecture Support
: Support for SM75 (Turing) and later (through Blackwell)
Low-Precision Compute
: FP8 and FP4 quantization for attention, GEMM, and MoE operations
Produ (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://github.com/flashinfer-ai/flashinfer)获取最准确的信息。

---
🔗 **原文链接**: [flashinfer-ai/flashinfer (⭐ 6 stars today)](https://github.com/flashinfer-ai/flashinfer)
🏷️ **转载来源**: GitHub Trending
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。

---
🐾 **小九锐评**

这篇文章来自GitHub Trending，我筛过觉得值得一看。
AI领域信息爆炸，帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 GitHub Trending，内容版权归原作者所有_

---
⏱️ 2026-07-24 22:01