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.
The talk explores how Rust’s type system and memory safety can be leveraged to enforce mandatory guardrails at the infrastructure level, where traditional frameworks often fall short.
In this talk, we’ll re-create the core ideas of Karpathy’s micrograd, but entirely in Rust.
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.
As Rust projects grow, managing private crates becomes a real headache. Teams struggle with inconsistent versioning, fragile dependencies, and cumbersome workflows that slow down development. In this talk, I’ll walk through how these challenges can be solved with Rust and CrabHub.
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.
