Bài kiểm tra có liên kết hướng dẫn · Trung bình Cấp độ

Bài kiểm tra tối ưu hóa mô hình suy luận trên CPU

Điều chỉnh suy luận của CPU thông qua các luồng, nhân thời gian chạy, lượng tử hóa, hành vi bộ nhớ và phép đo từ đầu đến cuối mà không cần giả sử một cài đặt nào sẽ thắng.

Đường dẫn hướng dẫn liên quanTối ưu hóa suy luận mô hình trên Cpus
Câu hỏi 1 của 8

Why can increasing CPU inference threads make a concurrent service slower?

Xem trước mọi câu hỏi8 câu hỏi

Câu trả lời và giải thích xuất hiện khi bạn làm bài kiểm tra.

  1. Why can increasing CPU inference threads make a concurrent service slower?
    • Additional threads always reduce memory use
    • Labels are removed when threads compete
    • Threads can oversubscribe cores and contend across requests
    • Vector instructions stop working when multiple requests arrive
  2. What can quantization trade against faster or smaller CPU inference?
    • Quantization removes the need for representative inputs
    • Lower precision can alter prediction quality
    • Quantization eliminates preprocessing costs
    • Quantization makes model versioning unnecessary
  3. Which overhead does operator fusion aim to reduce?
    • Số lớp đầu ra
    • Dataset licensing checks
    • The count of available CPU cores
    • Intermediate operations or data movement between compatible operators
  4. Why benchmark the exact deployment CPU and container limits?
    • Core availability, memory behavior, and instruction support affect runtime
    • The CPU model determines the task labels
    • Container limits change the model graph
    • Hardware has no effect on benchmark results
  5. What can dominate end-to-end latency even if model kernels are fast?
    • The title used to display the model
    • Training split identifiers
    • Tokenization, decoding, or feature preparation
    • The repository branch name
  6. How can batch size affect CPU serving?
    • Larger batches always reduce each request latency
    • Larger batches may improve throughput while adding wait and memory cost
    • Batch size affects accuracy but not serving resources
    • Batching has no relationship to CPU cache behavior
  7. What should be rechecked after quantizing or fusing a model?
    • Only compare the serialized model file size
    • Only verify the API route name
    • Only check that training loss was logged
    • Recheck prediction quality and input/preprocessing compatibility
  8. Which optimization workflow is most reliable?
    • Profile a baseline, change one factor, then compare quality and end-to-end speed
    • Maximize every thread setting without benchmarking
    • Change inputs and hardware between comparison runs
    • Measure only one warm forward pass