Disaggregated Speculative Decoding and Optimizing Inference Engines Across Chips

​Zoom link: https://us02web.zoom.us/j/82308186562

​Talk #0: Introductions and Meetup Updates

​by Chris Fregly and Antje Barth

​Talk #1: Disaggregated Speculative Decoding with d-Matrix Accelerators by Tom St. John, Head of Applied Research @ Gimlet Labs

​Tom will discuss and demonstrate disaggregated speculative decoding using d-Matrix chips on Gimlet Cloud.

​Talk #2: Optimizing Inference Engine Performance by Head of Engineering @ Makora

​Makora demos how to tune inference engine performance for the latest models and workloads.

​Zoom link: https://us02web.zoom.us/j/82308186562

​Related Links

​Github Repo: /cfregly/ai-performance-engineering

​O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/

​YouTube: /AIPerformanceEngineering

​Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm