Tokenization Is the Bottleneck You're Not Measuringranvier.systems1 points·by mindsaspire·hace 2 meses·1 comments
KV Cache Locality: The Hidden Variable in Your LLM Serving Costranvier.systems3 points·by mindsaspire·hace 2 meses·0 comments
24 Hard Rules for Writing Correct Async C++ranvier.systems3 points·by mindsaspire·hace 4 meses·0 comments
Show HN: Ranvier – Prefix-aware routing for LLM inferenceranvier.systems1 points·by mindsaspire·hace 4 meses·0 comments