LOADING
This talk explores building a complete self-hosted LLM stack in Rust: Paddler, a distributed load balancer for serving LLMs at scale, and Poet, a static site generator that consumes those LLMs for AI-powered content features.
This talk explores building a complete self-hosted LLM stack in Rust: Paddler, a distributed load balancer for serving LLMs at scale, and Poet, a static site generator that consumes those LLMs for AI-powered content features.
We'll dive into the hard problems: async request routing across dynamic agent fleets, integrating with llama.cpp's C++ codebase, managing KV cache in custom slots, and implementing zero-to-N autoscaling with request buffering. You'll see how Rust's ownership model prevented entire classes of bugs in distributed state management, and walk away with concrete patterns for building and consuming LLM infrastructure in production.
This technical talk examines the most prevalent pain points facing Rust web developers today and explores how the community is addressing them.
I contributed LTO-related changes to many open-source projects, and had a lot of interesting discussions with their maintainers about LTO. In this talk, I want to share with you my experience.
I'll initiate you in the art of 'CAN bus sniffing': Connecting to the central nervous system of a modern car, interpreting the data, and seeing what we can build as enthousiastic amateurs.
For infrastructure engineers, SREs, platform teams, and Rust developers who've felt the pain of configuration drift, failed deployments, and infrastructure code that simply doesn't scale safely.
I'll share a few tricks to help you write cleaner, more powerful declarative macros. You'll also get a sneak peek at the nightly features to see what's coming next macro_rules! world.
In this introductory talk, we will explore what it means to "Ratatuify" the Rust package manager, Cargo.
