Kuiz berkaitan panduan · Sederhana Tahap
Kuiz Inferens Berkelompok lwn Masa Nyata
Bandingkan kumpulan, penstriman dan inferens dalam talian mengikut kesegaran, kependaman, pemprosesan, kos dan operasi dalam sistem ML pengeluaran.
soalan 1 daripada 8
Beban kerja yang manakah sesuai secara semula jadi untuk inferens kelompok?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Beban kerja yang manakah sesuai secara semula jadi untuk inferens kelompok?
- Scoring next week's inventory forecasts overnight
- Blocking each payment until a score returns
- Responding to every chat token synchronously
- Updating a decision before a user clicks
- Mengapa menggunakan inferens masa nyata untuk keputusan kebenaran pembayaran?
- It has no latency requirement
- The decision is needed before the transaction proceeds
- It can always be computed the night before
- It avoids all service operation
- Apakah yang membezakan penstriman inferens daripada kerja kelompok setiap malam?
- It always returns an HTTP response to a user
- It only runs once per calendar year
- It processes arriving events continuously with bounded delay
- It uses no event ordering
- Reka bentuk yang manakah menggabungkan prapengiraan pukal dengan konteks permintaan baharu?
- It removes feature freshness concerns
- It eliminates all model-serving infrastructure
- It guarantees identical rankings for every user
- It combines efficient bulk work with fresh request context
- Apakah yang menyumbang kepada kependaman masa nyata hujung ke hujung?
- Only the model's matrix multiplication time
- Network, feature retrieval, preprocessing and postprocessing as well as model execution
- Training dataset size only
- The number of offline evaluation metrics
- Why can a real-time endpoint cost more than a scheduled job?
- Real-time models cannot be quantized
- Batch jobs always require more hardware
- Always-available capacity may sit idle between requests
- Requests have no network overhead
- What should a streaming system handle for late events?
- Static batch partition names only
- Only HTTP status codes
- The model's final training epoch
- Event-time windows, ordering and replay behavior
- Which principle should drive choosing among inference modes?
- Freshness, latency, throughput, cost and operational needs
- Always choose the lowest single-request latency
- Use the most complex infrastructure available
- Pick the mode with the newest model name