NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#llm-optimization

0 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedautonomous-agents1 drafting1 sparse-attention1 speculative-decoding1 systems-optimization1

2 stories, newest first · one card per story

Hugging Face daily papers7d ago

Multi-layer Indexer optimizes DeepSeek sparse attention

Multi-layer Indexer speeds DeepSeek-V3.2 decode up to 14.5% without retraining.

sparse-attention llm-optimization

Hugging Face daily papers7d ago

SpecPilot raises speculative decoding speedup from 4.46x to 10.87x

SpecPilot is an agentic loop that discovers algorithms and optimizations for speculative decoding across deployments.

speculative-decoding llm-optimization