Ikibazo gihuza ibibazo · Hagati Urwego
Igishushanyo mbonera cyo gushushanya Igishushanyo mbonera
Shakisha umushinga-wicyitegererezo cyifuzo, kugenzura intego, guhitamo kwangwa, amahirwe yo kwemerwa, ibimenyetso bya bonus, hamwe nakazi katerwa nakazi kihuta.
Ikibazo 1 Bya 8
Ni uruhe ruhare rwibanze rw 'umushinga' muburyo bwo gushushanya?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Ni uruhe ruhare rwibanze rw 'umushinga' muburyo bwo gushushanya?
- Gucomeka icyitegererezo kinini mubice bike burundu
- Guhindura ikibazo mu rundi rurimi
- Kugirango uhite usaba ibimenyetso byinshi byabakandida kuri moderi nini yo kugenzura
- Kubika ibiganiro byashize byo kugarura
- 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
- Bigenda bite kubimenyetso byateguwe nyuma yikimenyetso cya mbere icyitegererezo cyanze?
- Ibintu byose nyuma yambere idahuye birajugunywe
- Byose biremewe
- Boherejwe kuri moderi ya gatatu
- Barabitswe kandi bongeye gukoreshwa ubutaha
- 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
- 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
- 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
- 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)
- 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