← 🧠 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 leaves 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 sharply, and grouped-query attention sits between them by sharing key-value heads across small groups. AI, ML, and GenAI engineer 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
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?→ML Infrastructure & GPUsCompare LLM inference engines: vLLM, SGLang, TensorRT-LLM, TGI, and llama.cpp. What actually differs?→
COMPANIES THAT ASSUME THIS