Brussels / 1 & 2 February 2025

schedule

UB2.252A (Lameere)


Day Start End Track(s)
Saturday 10:30 → 18:45 Rust
Sunday 09:05 → 17:00 Low-level AI Engineering and Hacking
09 10 11 12 13 14 15 16 17 18
Saturday Augurs: a time series toolkit for Rust
 Building a watt-meter esp-rs and a rocket backend
 Huge graph analysis on your own server with WebGraph in Rust
 Bringing terminal aesthetics to the Web with Rust (and vice versa)
 Abusing reborrowing for fun, profit, and a safepoint garbage collector
 Type tips and tricks
 How I optimized zbus by 95%
 Programming ROS 2 with Rust
 Lessons from rewriting systems software in Rust
 Writing safe PostgreSQL extensions in Rust: a practical guide
 Rust-ifying the Linux kernel scheduler (in user space)
 Adventures in oxidizing Arch Linux Package Management
Sunday Hugging Face ecosystem for Local AI/ ML
 The Local AI Rebellion
 ZML: A High-Performance AI Inference Stack Built for Production and Multi-Accelerator Deployment
 History and advances of quantization in llama.cpp
 quantizing your GGUF models using iterative refinement of the importance matrix
 Apache Arrow: The Great Library Unifier
 Bringing AI to Wearable Systems: Integrating Vision, Audio, and Sensors on Constrained Hardware
 How Llamagator helps to implement LLM-as-a-Judge concept on your local machine
 Compositional LLMs for Assisted competitive coding
 The Model Openness Framework (MOF)
 Building AI Applications on Kubernetes: Leveraging Instructlab and the Bee Agent Framework
 GPUStack: Building a Simple and Scalable Management Experience for Diverse AI Models
 Self-hosted LLMs at a scale with Paddler
 RamaLama: Making working with AI Models Boring
 Building AI Applications from your desktop with Podman AI Lab
 From Supercomputer to Raspberry Pi: Building Open Source Polish Language Models
 Tricks Learned from Training Large Open-Source Models
 Synthetic Data: The Secret Ingredient in Better Language Models
 LLM Tool use in vLLM
 Scoping out the Tenstorrent Wormhole
 Building a new GGML backend: How, Challenges and Oppertunities with Novel Accelerators
 Porting GGML to the NUX Kernel Development Framework.
 Accelerating AI with open source hardware and software
 The bare metal perspective on AMD's GPU ASICs
 wllama: bringing llama.cpp to the web
 Milliwatt sized Machine Learning on microcontrollers with emlearn

Events

Title Speakers Track Start End

Saturday
  Augurs: a time series toolkit for Rust
 Ben Sully Rust 10:30 11:10
  Building a watt-meter esp-rs and a rocket backend
 Santiago Saavedra Rust 11:15 11:35
  Huge graph analysis on your own server with WebGraph in Rust
 Sebastiano Vigna Rust 11:40 12:20
  Bringing terminal aesthetics to the Web with Rust (and vice versa)
 Orhun Parmaksız Rust 12:25 13:05
  Abusing reborrowing for fun, profit, and a safepoint garbage collector
 Aapo Alasuutari Rust 13:10 13:50
  Type tips and tricks
 Nikolai Vazquez Rust 13:55 14:35
  How I optimized zbus by 95%
 Zeeshan Ali Khan Rust 14:40 15:20
  Programming ROS 2 with Rust
 Julia Marsal Perendreu Rust 15:25 15:45
  Lessons from rewriting systems software in Rust
 Ruben Nijveld Rust 15:50 16:30
  Writing safe PostgreSQL extensions in Rust: a practical guide
 Damien Clochard Rust 16:35 17:15
  Rust-ifying the Linux kernel scheduler (in user space)
 Andrea Righi Rust 17:20 18:00
  Adventures in oxidizing Arch Linux Package Management
 David Runge Rust 18:05 18:45

Sunday
  Hugging Face ecosystem for Local AI/ ML
 VB Low-level AI Engineering and Hacking 09:05 09:30
  The Local AI Rebellion
 Justine Tunney Low-level AI Engineering and Hacking 09:30 10:00
  ZML: A High-Performance AI Inference Stack Built for Production and Multi-Accelerator Deployment
 Rene Schallner, Guillaume Wenzek Low-level AI Engineering and Hacking 10:00 10:30
  History and advances of quantization in llama.cpp
 Tanya Dadasheva, Iwan Kawrakow Low-level AI Engineering and Hacking 10:30 11:00
  quantizing your GGUF models using iterative refinement of the importance matrix
 Robert Collins Low-level AI Engineering and Hacking 11:00 11:20
  Apache Arrow: The Great Library Unifier
 Matthew Topol Low-level AI Engineering and Hacking 11:20 11:50
  Bringing AI to Wearable Systems: Integrating Vision, Audio, and Sensors on Constrained Hardware
 Kris Kersey Low-level AI Engineering and Hacking 11:50 11:55
  How Llamagator helps to implement LLM-as-a-Judge concept on your local machine
 Sergy Sergyenko Low-level AI Engineering and Hacking 11:55 12:00
  Compositional LLMs for Assisted competitive coding
 Ritwik Agarwal Low-level AI Engineering and Hacking 12:00 12:05
  The Model Openness Framework (MOF)
 Arnaud Le Hors Low-level AI Engineering and Hacking 12:05 12:10
  Building AI Applications on Kubernetes: Leveraging Instructlab and the Bee Agent Framework
 Martin Hickey, Paul Schweigert Low-level AI Engineering and Hacking 12:10 12:15
  GPUStack: Building a Simple and Scalable Management Experience for Diverse AI Models
 Lawrence Li Low-level AI Engineering and Hacking 12:20 12:40
  Self-hosted LLMs at a scale with Paddler
 Mateusz Charytoniuk Low-level AI Engineering and Hacking 12:40 13:00
  RamaLama: Making working with AI Models Boring
 Eric Curtin Low-level AI Engineering and Hacking 13:00 13:20
  Building AI Applications from your desktop with Podman AI Lab
 Cedric Clyburn, Stevan Le Meur Low-level AI Engineering and Hacking 13:20 13:40
  From Supercomputer to Raspberry Pi: Building Open Source Polish Language Models
 Bielik Team, Maciej, Pawel Cyrta, Adrian Low-level AI Engineering and Hacking 13:40 13:55
  Tricks Learned from Training Large Open-Source Models
 Marcus Edel Low-level AI Engineering and Hacking 13:55 14:10
  Synthetic Data: The Secret Ingredient in Better Language Models
 Carol Chen, Cedric Clyburn Low-level AI Engineering and Hacking 14:10 14:25
  LLM Tool use in vLLM
 Max de Bayser Low-level AI Engineering and Hacking 14:25 14:40
  Scoping out the Tenstorrent Wormhole
 Peter Cawley Low-level AI Engineering and Hacking 14:40 15:00
  Building a new GGML backend: How, Challenges and Oppertunities with Novel Accelerators
 Martin Chang Low-level AI Engineering and Hacking 15:00 15:20
  Porting GGML to the NUX Kernel Development Framework.
 Gianluca Guida Low-level AI Engineering and Hacking 15:20 15:40
  Accelerating AI with open source hardware and software
 William Jones Low-level AI Engineering and Hacking 15:40 16:00
  The bare metal perspective on AMD's GPU ASICs
 Jon Chesterfield Low-level AI Engineering and Hacking 16:00 16:20
  wllama: bringing llama.cpp to the web
 Xuan-Son Nguyen Low-level AI Engineering and Hacking 16:20 16:40
  Milliwatt sized Machine Learning on microcontrollers with emlearn
 Jon Nordby Low-level AI Engineering and Hacking 16:40 17:00