CrackML by @ml.with.umang
Interview questions / GenAI & LLM
GenAI & LLM interview question

Explain the architecture of an LLM serving stack built around vLLM.

Explain the architecture of an LLM serving stack built around vLLM.

hardsystem designEvidence 41/1001 source reportNVIDIA

The 60-second answer

Break end-to-end latency into queueing, preprocessing, host/device transfer, kernel execution, synchronization, decoding, and post-processing before optimizing. Profile utilization, memory bandwidth, occupancy, batch shape, cache behavior, and p50/p95/p99 latency to identify whether the bottleneck is compute, memory, launch overhead, or scheduling.

Build the answer in this order

1
Define the mechanism

Break end-to-end latency into queueing, preprocessing, host/device transfer, kernel execution, synchronization, decoding, and post-processing before optimizing.

2
Explain the architecture

Profile utilization, memory bandwidth, occupancy, batch shape, cache behavior, and p50/p95/p99 latency to identify whether the bottleneck is compute, memory, launch overhead, or scheduling.

3
Compare trade-offs

Apply batching, kernel fusion, mixed precision, caching, layout changes, or paged/continuous-batching techniques only when profiling supports them.

4
Close with serving + evaluation

Validate under realistic concurrency and sequence-length distributions while tracking throughput, tail latency, memory headroom, and failure rate.

A useful interview mental model

This is the shape of a strong answer—not a script to memorize.

01Requirements
02Data
03Model / Retrieval
04Serving
05Monitor

Senior-level signal

  • Design admission control and backpressure so throughput gains do not create OOMs or catastrophic tail latency.
  • Tie kernel-level wins to end-to-end request performance; microbenchmarks alone are not a production success metric.

What the interviewer is really testing

Understanding beyond prompting: architecture, retrieval, evaluation, inference, safety, latency, cost, and failure recovery.

Likely follow-up questions

What changes at 10× traffic or data volume?
Which failure mode would you monitor first in production?
How would you evaluate this offline and online before rollout?

Common weak-answer patterns

  • Jumping to a model before defining the product contract.
  • Listing components without bottlenecks, metrics, or failure handling.
  • Ignoring data quality, serving latency, monitoring, and iteration.