Easily deploy any Hugging Face model behind a private API with LitServe! LitServe simplifies model deployment, offers use on multiple GPUs, and more. Try it for yourself: https://lnkd.in/en7y6wvv
Lightning AI
Software Development
New York, NY 86,084 followers
The AI development platform - From idea to AI, Lightning fast⚡️. Creators of AI Studio, PyTorch Lightning and more.
About us
The AI development platform - From idea to AI, Lightning fast ⚡️. Code together. Prototype. Train on GPUs. Scale. Serve. From your browser - with zero setup. AI Studio is your laptop on the cloud. Zero setup. Always ready. Persistent storage and environments. Code on CPU. Debug on GPU. Scale to multi-node. Run sweeps, jobs and more. Scale models with PyTorch Lightning, Fabric, Lit-GPT, torchmetrics and more.
- Website
-
http://lightning.ai
External link for Lightning AI
- Industry
- Software Development
- Company size
- 11-50 employees
- Headquarters
- New York, NY
- Type
- Privately Held
- Founded
- 2019
- Specialties
- Artificial Intelligence, Machine Learning, Infrastructure, deep learning, data science, and open source
Locations
-
Primary
New York, NY, US
Employees at Lightning AI
Updates
-
In our latest ‘Thunder Sessions’ podcast, Luca Antiga and Thomas Viehmann write a Thunder fusion transform and then enjoy the utility of it. Watch the full episode here: https://lnkd.in/ewwHnC8b
-
🤯 RWKV makes AI more accessible, requiring 10-100x lower compute vs transformer-based LLMs for the same performance! 💪 Shipped with Windows 11, it’s now one the world’s most widely deployed, open-source (Apache 2.0) LLMs ⚡Trained with PyTorch Lightning See how it's changing the game ➡️ https://wiki.rwkv.com/
-
Boost your AI models with Thunder & Triton! 🚀 Last week in the Thunder Sessions, @lantiga & @ThomasViehmann built a triton matmul kernel using the flexibility of thunder executors to insert it into their model. Join us tomorrow Fri, Sep 6 @ 11am ET to learn about kernel fusion techniques: https://lnkd.in/ezPU5phZ Until then check out our previous episodes: https://lnkd.in/e9U9Gh9h
The Thunder Sessions | Session 7 | Fusing Kernels with Thunder & Triton
https://www.youtube.com/
-
🚀 Boost your model serving speed by over 8x with LitServe's dynamic batching and autoscaling. 💫 Its easy-to-use, Python API simplifies model serving at high concurrency, merging speed with flexibility. 🔥 Get the best of both worlds https://lnkd.in/gbA4vvEk
-
🚀 Exciting news! Arda Göreci and team at Ligo Biosciences have fully reproduced AlphaFold3, making the state-of-the-art in AI-driven protein folding accessible to all! 🌟 Arda Göreci: “PyTorch Lightning and its ecosystem has been essential for developing this project in a short period of time.” ⚡️ We couldn’t be happier 🥳 Check it out: https://lnkd.in/ey6aZfUu
-
LitServe is an easy-to-use, flexible serving engine for AI models built on FastAPI. Features like batching, streaming, and GPU autoscaling eliminate the need to rebuild a FastAPI server per model. 🤯 LitServe is at least 2x faster than plain FastAPI due to AI-specific multi-worker handling. Supercharge your serving https://lnkd.in/ecU32_cr
-
Join the biggest online community for open source AI by joining the Lightning AI Discord. 📣 Exclusive live-events 💁♂️ Support from experts 🤝 Networking building Join the conversation on Discord: https://lnkd.in/d6N2QD53
-
Today’s Thunder Sessions goes live at 11am ET! Today’s topic: More transforms and less theory 🔄 > 📚 Join Luca Antiga and Thomas Viehmann on the livestream: https://lnkd.in/e9APy2aG
The Thunder Sessions | Session 6 | More Transforms and Less Theory
https://www.youtube.com/
-
Catch the next Thunder Sessions livestream this Friday, Aug 30 at 11am EST and see how Thunder, our source to source compiler, makes AI models 40% faster. Luca Antiga & Thomas Viehmann go deeper with more transforms and less theory. ⚡ 🏃♂️ Catch up on the previous sessions https://lnkd.in/e9U9Gh9h 👀 Before you watch it live https://lnkd.in/eES-NJtD