Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Tokenization Is the Bottleneck You're Not Measuring (ranvier.systems)
1 point by mindsaspire 18 hours ago | past | 1 comment
KV Cache Locality: The Hidden Variable in Your LLM Serving Cost (ranvier.systems)
1 point by gmays 20 days ago | past
KV Cache Locality: The Hidden Variable in Your LLM Serving Cost (ranvier.systems)
3 points by mindsaspire 25 days ago | past
24 Hard Rules for Writing Correct Async C++ (ranvier.systems)
3 points by mindsaspire 57 days ago | past
Show HN: Ranvier – Prefix-aware routing for LLM inference (ranvier.systems)
1 point by mindsaspire 69 days ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: