OpenClaw/MoltBot/ClawdBot/MCP + NVFP4 Low Precision for AI System Optimizations

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

​Talk #0: Introductions and Meetup Updates [5 mins] by Chris Fregly and Antje Barth

​Talk #1: OpenClaw/MoltBot/ClawdBot/MCP for GPU Kernel and AI System Optimizations [10 mins] by Chris Fregly

​In this demo, Chris will demonstrate how to use both MCP and OpenClaw (formerly all the other names used in the talk title!) to optimize GPU kernels and complete end-to-end AI systems.

​Related Link: Github Repo for these tools: https://github.com/cfregly/ai-performance-engineering/

​Talk #2: Unlocking NVFP4: Low Precision Numerics on NVIDIA Blackwell [30-45 mins] by Riccardo Mereu @ Verda.com

​In this talk, Riccardo dives deep into low-precision numerics, model quantization algorithms, on NVIDIA Blackwell including NVFP4 (vs. MXFP4), per-block scaling, per-tensor scaling, mixed precision, and much more!

​Related link: GPU Mode NVFP4 GEMM kernel competition blog post by Daniel Obolensky: https://obolensky.xyz/blog/nvfp4_gemm_kernel_explanation/

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

​Related Links

​Github Repo: http://github.com/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