Quiz de modèle de projet de décodage speculatif

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

1. Lan mooy cër bu njëkk bi ci xeetu 'projet' ci dekodage spekulatif?
   • Ngir kompresse model bu rëy bi ci paramet yu néew ba fàww
   • Tekki laaj bi ci beneen làkk
   • Ngir gaaw proposer ay token kandidaa ngir model bu mag bi ngir xool
   • Ngir denc waxtaan yi weesu ngir seetaat
2. Why can verifying a drafted token block accelerate target-model generation in a suitable workload?
   • Verification has no compute cost at any block size
   • A verification pass can process several positions together and amortize target work across accepted tokens
   • The draft model is guaranteed more accurate than the target
   • The target model is skipped for every accepted token
3. Lan mooy dall token yiñ bind ginaaw token bi njëkk bi model biñ bëgga bañ?
   • Lépp ginaaw ñàkka méngoo bu njëkk bi dañu koy sànni
   • Ñoom ñépp ñu ngi leen nangu
   • ñu yónnee leen ci ñatteelu xeetu
   • Dañu leen denc ci cache ba noppi jëfandikoowaat leen beneen yoon
4. What correctness property does the standard exact speculative-sampling rejection procedure preserve under its assumptions?
   • An identical random sequence for every possible random seed
   • Guaranteed truth of every generated statement
   • The draft model's distribution regardless of the target
   • The target model's configured sampling distribution
5. Which mechanism distinguishes EAGLE's drafting approach from Medusa's additional decoding heads?
   • EAGLE performs only word-count-based lexical retrieval
   • EAGLE drafts autoregressively at the target model's feature level
   • EAGLE removes target verification from every algorithm
   • EAGLE and Medusa are the same architecture with different names
6. Why should a speculative-decoding benchmark report the draft-target pair and acceptance rate?
   • Every model pair has the same guaranteed speedup
   • Acceptance rate measures whether generated facts are true
   • Speedup depends on drafting and verification costs and how many proposed tokens are accepted
   • The target model's hardware and context length cannot affect performance
7. In exact speculative sampling, a proposed token has q equal to 0.2 and p equal to 0.1. What is its acceptance probability?
   • 0.1, because only p is used
   • 0.2, because only q is used
   • 1.0, because every proposed token is accepted
   • 0.5, from min(1, p/q)
8. What can the standard speculative-sampling algorithm emit when every token in a drafted block is accepted?
   • The accepted block plus an additional token sampled from the target
   • Only the last drafted token, discarding the accepted prefix
   • An arbitrary extra draft token without target sampling
   • No output until the draft model is retrained