Browse by format or topic. To see where I’ve delivered them, visit my speaking page and my events. Want one of these at your event? Get in touch.
No talks match this filter.
What happens when you send a chat request to an LLM? We trace a single request to GPU and back. We will also look at all systems that make up inference pipeline and optimizations
Using open models with modern coding agents for practical software development.
Practical techniques for improving LLM inference latency, throughput, and cost, with benchmarks and production examples.
Enable OpenClaw with real time search with Tavily + Token Factory
Build apps with open models
Hands-on with Nebius Token Factory
Post training best practices for open LLMs.
Prepare and process documents with Docling and Data Prep Kit, then connect retrieval with Milvus and open LLMs.
Build a website question-answering application with an open stack, from collecting and indexing content to retrieval and a chat interface.
Prepare data for LLM applications with an open-source toolkit for cleansing, transforming, and enriching unstructured data.