May 31, 2024May 31, 2024 · 12 min read · 2.0K viewsEssential Math & Concepts for LLM InferenceBack of the envelope calculations to estimate model's GPU memory requirements & insights into HW/SW optimizations12 min read · 2.0K views
Apr 8, 2024Apr 8, 2024 · 16 min read · 795 viewsCPU & GPU - The BasicsA digestible high-level overview of what happens in The Die16 min read · 795 views