AI Performance Engineering

About

All things AI performance related including PyTorch, CUDA, and GPUs.

Events

• Hacking AI Accelerators: Maxxing Tokens & Outcomes with Rob Ferguson @ Fireworks.AI 2026-06-15
• OpenAI on AWS (!!) + Cerebras vs GPU vs TPU + High-Performance KV Cache Offload 2026-05-18
• NVIDIA GTC 2026 Conf Recap + Inference Disagg Prefill-Decode + RadixAttention 2026-03-23
• OpenClaw/MoltBot/ClawdBot/MCP + NVFP4 Low Precision for AI System Optimizations 2026-02-16
• Nvidia Nsight GPU Profiling + KV Cache Efficiency + Context "Platform" Engineering 2026-01-19
• NVIDIA CuML, DBSCAN, tSNE: Accelerated LLM Data Curation/Visualization + Neurips 2025 AI Performance Recap 2025-12-15
• Speed of Light Inference w/ Modular + Data Curation/Visualization w/ NVIDIA CuML 2025-11-17
• Generative AI on AWS: Building Meta XR Apps, Agentic Code Interpreter, Multi-Modal RAG 2024-08-28
• Generative AI on AWS 2024-01-15