Custom quantization scheme found via greedy and evolutionary search, Pareto optimal
giffmana · x · 2026-10-21
Tim Darcet describes finding a custom quantization scheme through search (greedy and evolutionary) that minimizes both memory footprint and perplexity error, identifying two optimal tradeoffs and confirming Pareto optimality. giffmana jokes about why no agentic search, betting the author will explore that next.
More from Research
- AI agents with $10,000 budgets still fail open-ended research: GPT-6 Astra and Fable 5.1 papers rejected — sayashk · 2026-10-21
- Stanford team launches ScholarCatalyst, a benchmark for literature retrieval that inspires research — lateinteraction · 2026-10-21
- Simple symmetric Venn diagrams with 17, 19 and 23 curves found via AI-assisted search, verified in Lean 4 — pickover · 2026-10-21
- Pathway CEO in Forbes: Transformers Won't Get Us to Superintelligence, Experience-Learning AI Will — schwentker · 2026-10-21
- Laude Institute Backs Stanford's CLMs: Contrastive Language Models for Fast Decision-Making — Azaliamirh · 2026-10-21
- UC Berkeley releases Actor-Gatherer framework decoupling reasoning from context management — adityagp · 2026-10-21