Kir Zharov’s Post

📢 Join us next Thursday for the London PyTorch Meetup #22 at Skyscanner 🏢 We are planning: 3 talks, networking, 🍕, 🍺, and afterparty at a pub. Speakers - Antoni Shtipliyski: "Applied ML at Skyscanner" We will walk you through the problem domain that Skyscanner is serving and how ML helps us bring more value to the traveller. We will give you examples of characteristic problems we are solving and our efforts to make the problem more repeatable through the development of our realtime publishing and serving platform. - Kirill Solodskih, Solodskikh: "Accelerating Neural Networks Through Quantization in PyTorch for Different Devices" We design and apply quantization algorithms for PyTorch DNNs across modern architectures, using PyTorch internals mechanisms to automatically balance quality and speed. We then compile the quantized checkpoints to deliver real-world speedup on different hardware. - Aniket Maurya: "How to fine-tune an open-source LLM and deploy it in Production" I will show how to easily fine-tune an open source model with LoRa and how to deploy it to Production with LitServe. 🤝 Thanks to Vultr for sponsoring this event! 🚨 Spots are limited, less than 45 spots are left. 👉 Secure your spot here: https://lu.ma/lwzz7g9r or via Meetup com (link in comments). If you want to give a talk or collaborate, message Fedor Shabashev or Kir Zharov. Please share this event with your colleagues ❤️ See you next week!