Kediska Duubista Joogtada ah

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay daciifnimada ugu weyn ee kaydinta joogtada ah (go'an) ee adeega LLM?
   • Waxay ku socon kartaa oo keliya CPU-yada
   • Waxay u baahan tahay in marka hore la calaamadiyo dhammaan xogta
   • Codsiyada gaagaaban goor hore ayay dhammaadaan laakiin boosashoodu waa shaqo-la'aan inta ay qaybtu sugayso tan ugu dheer
   • Waxay ka dhigaysa qaabka mid sax ah
2. Immisa kala duwanaansho ah ayay ku daraa oo ka saartaa codsiyada?
   • Hal mar maalintii
   • Tallaabo kasta oo codeed (hal calaamad markiiba)
   • Codsi buuxa oo keliya
   • Xilligii tababarka
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. Farsamokee ku lammaan si dabiici ah iyo dufcad joogto ah si ay gelinta/saarida taxanaha uga dhigto mid jaban?
   • Kaydinta KV-ku-saleysan ee PagedAttention
   • FP32 sax labanlaab ah
   • Isku beddelashada diskka
   • Calaamadaynta xogta gacanta
5. Waa maxay warqadda cilmi-baarista ee sida caadiga ah lagu tiriyaa caannimada heerka-soo-celinta (sii-socota)?
   • Warqadda Transformer ee asalka ah
   • Warqadda Orca
   • Warqad xog-ururin 1980-yadii
   • Warqadda ImageNet
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