lazycodex
The agent harness for complex codebases inside Codex — project memory, planning and verified completion.
FlashAttention ist ein Open-Source-Projekt aus der Kategorie Entwickler-Tools von Dao-AILab (Dao-AILab/flash-attention auf GitHub). Es hat 25.236 Sterne auf GitHub und 3.201 Forks, wird unter der Lizenz BSD-3-Clause veröffentlicht und wurde zuletzt am 2. November 2026 auf GitHub aktualisiert.
FlashAttention — fast, memory-efficient exact attention that lets transformers handle long sequences, BSD-3-Clause
Install flash-attn-4 from PyPI, or the CUDA 13 variant if that matches your toolkit.
Use the flash-attn-3 interface from your model code where the library is integrated.
For configurations without a matching wheel, build from source with ninja installed and build isolation disabled.
The same attention maths as standard transformers — faster and leaner, without changing results.
Avoiding the full attention matrix is what lets models handle long contexts on the same hardware.
CUDA kernels for NVIDIA GPUs, with a Triton path documented for AMD GPUs.
Integrated across the model ecosystem — the attention implementation behind much of modern LLM training and inference.
The README install route for flash-attn-4.
pip install flash-attn-4The README variant for CUDA 13 toolkits.
pip install "flash-attn-4[cu13]"The README source-build route for setups without a matching wheel.
pip install flash-attn --no-build-isolationThe Dao-AILab team, as the exact-attention kernel library.
Yes — BSD-3-Clause licensed.
No — it computes exact attention, the same maths as standard attention, just faster and with less memory.
Usually not — prebuilt flash-attn-4 wheels cover common setups; source builds with ninja are for configurations the wheels do not cover.
pip install flash-attn-4 (or the CUDA 13 variant), then use it through a framework that integrates it.
The agent harness for complex codebases inside Codex — project memory, planning and verified completion.
The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.
Fine-tune huge models on small hardware with LoRA and other efficient methods
A virtual terminal and filesystem that lets AI agents work across S3, Drive, Slack, Gmail and more.
A portable home for your AI agent — memory, keys and automations on Cloudflare.
Persistent memory for coding agents — frozen, but its core lives on in Caveman.
Die anderen Projekte der Kategorie Entwickler-Tools mit den meisten Sternen im LibreAI-Katalog — die realistische Auswahl, falls FlashAttention nicht das Richtige ist.
The open source coding agent
The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.
Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase
Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents
OpenAI's lightweight coding agent that runs locally in your terminal
Verwandte Projekte der Kategorie Entwickler-Tools im Katalog, die FlashAttention bei den Sternen am nächsten stehen — zum Weiterstöbern auf beiden Seiten.
TOON: a compact, human-readable serialization of JSON that saves tokens in LLM prompts
A 25MB database client for 100+ databases — with a built-in AI assistant, MCP server and CLI
Context optimization for coding agents: sandbox tool output, keep sessions lean, remember more
A desktop GUI and toolkit for Claude Code - agents, sessions, analytics and MCP
Vercel's AI SDK: the TypeScript toolkit for building AI apps and agents with any model provider
Hugging Face's library for loading and processing datasets for AI models in one line
Kostenlos und offen — hol dir den Quellcode, gib dem Repository einen Stern und leg los.