← 🧠 Foundations of LLMs & GenAINEXT IN FOUNDATIONS OF LLMS & GENAIPositional Encodings (RoPE and ALiBi)→
Core
Attention Variants: MHA, MQA, and GQA
Multi-head attention gives every query head its own key and value heads, which is expressive but makes the KV cache large and memory-bandwidth hungry at decode time. Multi-query attention shares one key-value head across all query heads to shrink the cache hard, and grouped-query attention sits in between by sharing key-value heads across small groups. Applied-AI interviews probe this because it is the cleanest example of trading model quality against serving memory and throughput, and it explains why frontier models standardized on GQA.
a free account unlocks the core curriculum tier · no card
COURSES COVERING THIS TOPIC
No lesson covers this one directly yet. These teach the surrounding topic from the beginning.
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
ML Infrastructure & GPUsServe a 70B-parameter model with high throughput. Do the memory math and name the optimizations.→ML Infrastructure & GPUsExplain the KV cache: prefill vs decode, why it grows, and how MQA/GQA and PagedAttention help.→LLM & GenAI FundamentalsWhat are Multi-Query (MQA) and Grouped-Query Attention (GQA), and why do they exist?→ML Infrastructure & GPUsHow does prefix caching work internally in an LLM server, and when does it actually help?→ML Infrastructure & GPUsReasoning models made your traffic decode-heavy: 30k thinking tokens per request. What changes in your serving stack?→LLM & GenAI FundamentalsWhat is PagedAttention, and why did it transform LLM serving throughput?→
COMPANIES THAT ASSUME THIS