Sign in
← Back to search

flashinfer-ai/flashinfer

FlashInfer: Kernel Library for LLM Serving

#attention#cuda#distributed-inference#gpu#jit#large-large-models#llm-inference#moe#nvidia#pytorch
Sign in to like flashinfer-ai/flashinfer Open website Open GitHub
Stars
5,674
Forks
994
Commits
2334
Language
Python
Awesome lists
1

Similar repositories

Tiiny-AI/PowerInfer

High-speed Large Language Model Serving for Local Deployment

9494 stars
C++ 1 awesome list

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

81308 stars
Python 3 awesome lists

OptimalScale/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

8486 stars
Python 2 awesome lists

sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

28241 stars
Python 4 awesome lists

jd-opensource/xllm

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

1300 stars
C++ 1 awesome list

Tracked growth

1 capture since 2026-05-25

Latest capture 2026-05-25 20:57

Stars history

Total stars

Commits history

Default branch commits

Metadata

  • Created: 2023-07-22
  • First commit: —
  • Last pushed: 2026-05-25
  • Website: https://flashinfer.ai
  • Archived: no
  • Stack detected: —
  • License: Apache-2.0

AI development signals

AI agent config detected

10 config paths 5 files 5 directories
Agent instructions Claude Code 9

Key config paths

  • dir .claude
  • file AGENTS.md
  • file CLAUDE.md
Review config paths
  • Claude Code .claude
  • Claude Code .claude/skills
  • Claude Code .claude/skills/add-cuda-kernel
  • Claude Code .claude/skills/add-cuda-kernel/SKILL.md
  • Claude Code .claude/skills/benchmark-kernel
  • Claude Code .claude/skills/benchmark-kernel/SKILL.md
  • Claude Code .claude/skills/debug-cuda-crash
  • Claude Code .claude/skills/debug-cuda-crash/SKILL.md
  • Agent instructions AGENTS.md
  • Claude Code CLAUDE.md