Multiple Choice

Identify the workload pattern where a traditional ANN-indexed vector database is the wrong tool, and a log-structured or batch-rebuild approach fits better.

Pick the right vector database for a startup with 2M documents, no DevOps headcount, and a one week launch deadline.

A vendor's benchmark chart plots QPS against recall@10. What should you look for, and what claim should make you skeptical?

PQ-based distance computation outruns full float32 distance even after decoding the vectors. Why?

At what scale does 'just put it in Postgres with pgvector' stop being the right answer?

What does Matryoshka representation learning buy a vector-database operator beyond regular embeddings?

Modern vector databases combine sparse (BM25) and dense vectors at the storage layer via two distinct patterns. Identify them.

As M grows in an HNSW index, four things move at once. Identify what climbs versus what slows.

Pre-filter versus post-filter strategies for metadata-constrained ANN search — what breaks at each extreme?

What problem does DiskANN solve that HNSW does not, and when do you reach for it?

Doubling the embedding dimension from 768 to 1536 — what changes in storage, query latency, and PQ trainability?

Cosine similarity and dot product give identical rankings under exactly one condition. Which is it?

When does binary quantization beat Product Quantization as the production compression choice for a vector index?

Why does every production retrieval system use approximate nearest-neighbor search instead of exact search past a certain corpus size?

Why does the transformer block use LayerNorm or RMSNorm instead of BatchNorm?

Pick the recipe a 2026 frontier open-weight LLM block actually ships

What does 'position-wise' actually mean for the transformer FFN sublayer?

Which sublayer of a dense transformer block carries more parameters, attention or FFN?

Pick the 2026 task where an encoder-only transformer still beats a decoder-only LLM

What fraction of a 7B transformer lives in its embedding table at vocab 128k?

Speculative decoding is already on and batch size just climbed to 64, keep it or kill it?

For 1M-token context decode, which parallelism axis actually relieves KV pressure?

Heavy multi-turn chat shares system prompts across requests, pick the serving framework that exploits that best.

At batch 16 and 4k context with FP8 weights, which model still fits on one 80 GB H100?

Which deployment shape best meets a strict P99 TPOT SLA on bursty traffic?