@prefix schema: <https://schema.org/> .
@prefix af: <https://anchorfact.org/ns#> .

<https://anchorfact.org/kb/ai/llm-inference-optimization>
  a schema:TechArticle ;
  schema:headline "LLM Inference Optimization: From FlashAttention to Speculative Decoding" ;
  schema:url <https://anchorfact.org/ai/llm-inference-optimization/> ;
  af:status "public" ;
  af:confidence "medium" ;
  af:confidenceScore "0.82" ;
  af:confidenceBasis "verified_sources" ;
  af:generationMethod "ai_structured" .

<https://anchorfact.org/kb/ai/llm-inference-optimization>
  schema:citation <https://arxiv.org/abs/2309.06180> ;
  af:sourceTier "A" .

<https://anchorfact.org/kb/ai/llm-inference-optimization>
  schema:citation <https://arxiv.org/abs/2205.14135> ;
  af:sourceTier "A" .

<https://anchorfact.org/kb/ai/llm-inference-optimization>
  schema:citation <https://arxiv.org/abs/2208.07339> ;
  af:sourceTier "A" .