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 talk puts popular Rust rewrites to the test. We'll examine how these tools stack up against their battle-tested predecessors, looking at real-world performance, compilation times, binary sizes, feature completeness, and ecosystem maturity.
In my session, I will present the https://hotpath.rs crate and explain how it compares to other profiling tools available.
This session we will delve into the sometimes murky world of procedural macros - showing some of the great tooling available for understanding the code generated, such as cargo expand, and the key building blocks we will need for writing our own.
