IEEE plenary talk: micro-optimizations across the full stack, from silicon to models
fooobar · x · 2026-09-25
The author returned to an IEEE stage as a plenary speaker with a talk titled "Micro-Optimisations for Macro-Impact," covering the importance of identifying and resolving bottlenecks throughout the stack — from silicon to models — to do more with less. The post only summarizes the talk without technical specifics.
More from Infra
- Former Intel CEO calls HBM "lousy" at Hot Chips 2026 as High Bandwidth Flash looms — Glittering_Depth_722 · 2026-09-25
- MLPerf Training v6.1 adds first LLM post-training benchmark: agentic RL on a 397B model — TheKanter · 2026-09-25
- kvcached brings virtual memory to LLM KV cache, deployed on 10K+ GPUs — techNmak · 2026-09-25
- Dev builds local AI GTM workflow, argues the next platform entry point is hardware-bound — dotey · 2026-09-25
- US Faces Memory Chip Conundrum as AI-Critical Prices Skyrocket, WSJ Reports — pstAsiatech · 2026-09-25
- Qwen Flash Next IQ4_XS beats 27B FP8 on MMLU-Pro, GPQA and GSM8K in community eval — smallDeltaBigEffect · 2026-09-25