quiz bu lëkkale ak tegtal · Dëgër Niveau

Quiz buy wéy

Jëfandikool niveau iterasioŋ LLM batching, àppu kàttan, ak kompromis prefill, boole ci lu tax nangu sàq yi wéy di gaaraati zero xaar.

Yooni njiit yu jëm ciBatching bu wéy
Laaj 1 de 8

Lan mooy ñakk kattan gi gëna mag ci batching static (fixe) ngir liggéey LLM?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan mooy ñakk kattan gi gëna mag ci batching static (fixe) ngir liggéey LLM?
    • Mën na dox ludul ci CPU
    • Dafay laaj nga njëkka etikete done yépp
    • Laajte yu gàtt yi dañuy teela jeex waaye seeni barab duñu def dara ci diir bi batch bi di xaar bi gëna gudd
    • Dafay tax model bi gëna néew
  2. Ci yan granularite la batching biy wéy di yokk wala di dindi ay laaj?
    • Benn yoon ci bis bi
    • Jéego bu nekk ci dekodage (benn jeton benn yoon)
    • ci laaj bu mat sëkk
    • ci jamonoy tàggat yaram
  3. A continuous-batching request finishes and frees capacity. What can the scheduler do next?
    • Restart every remaining request from its first token
    • Guarantee every queued request runs immediately
    • Discard the finished answer without returning it
    • Admit eligible queued work if its resource budgets allow
  4. Ban pexe mooy méngoo bu baax ak batching bu wéy ngir mëna dugal/dindi ay toppalante yu yomb?
    • Cache KV bu lalu ci bloku PagedAttention
    • FP32 ñaari yoon
    • Weccoo disk
    • Etiketu done ci loxo
  5. Ban këyitu gëstu lañu gëna wax ni moo siiwal batching bi ci niveau iteration (di wéy)?
    • Këyit Transformatër bu njëkk bi
    • Papier Orca
    • Këyitu base de done ci ati 1980
    • Këyitu ImageNet bi
  6. What utilization problem can continuous batching reduce compared with a fixed request batch?
    • Every model accuracy error
    • The need to store any KV cache
    • All queueing at any traffic rate
    • Waiting for the longest request before admitting new eligible work
  7. A continuous-batching server has reached its memory budget. Must a newly arrived request enter the next iteration?
    • No; admission can wait until suitable capacity is available
    • Yes; the name guarantees unlimited request admission
    • Yes; the server removes all active outputs automatically
    • Only if the request has no punctuation
  8. A long prompt’s prefill delays tokens for already decoding requests. Which serving objective exposes that tradeoff?
    • Measure only the weight-file name
    • Assume more admitted prompts always improve every latency
    • Measure time between decode tokens alongside throughput
    • Count only the number of model layers