PagedAttention

Name the architectural shifts vLLM v1 made relative to v0

vLLM defaults to a page size of 16. Pick what makes 1 and 1024 worse choices.

Describe how continuous batching interacts with the KV cache

How does prefix KV-cache sharing reduce serving cost across requests?

How does PagedAttention enable prefix sharing across requests and what data structure makes it cheap?

Match each production serving framework to its defining strength

What does the vLLM-style continuous-batching scheduler actually do at each step?

Put the vLLM-style continuous-batching scheduler steps in correct order for one iteration

Walk through paged attention end to end, page table, block lookup, and how it enables higher throughput.

What problem does paged attention (vLLM) solve, and what OS concept does it borrow from?