TensorRT dan Kuiz Enjin Inferens

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

1. What is the goal of building an inference engine with TensorRT?
   • Guarantee the fastest possible execution on every system
   • Optimize execution of a supported trained model for the configured target
   • Choose training labels without a dataset
   • Replace every GPU with a CPU
2. Bagaimanakah pelakuran lapisan mempercepatkan inferens?
   • Dengan menggabungkan berbilang operasi ke dalam satu kernel GPU untuk mengurangkan trafik memori
   • Dengan memadam lapisan yang tidak diperlukan
   • Dengan menjalankan setiap lapisan pada GPU yang berasingan
   • Dengan menukar model untuk dijalankan pada CPU
3. In a representative-data INT8 calibration workflow, why examine the model’s value distributions?
   • To guarantee no accuracy change under all future inputs
   • To retrain the model from zero automatically
   • To select quantization scales suited to the observed numerical ranges
   • To remove every compatibility requirement
4. Mengapakah enjin TensorRT yang disusun secara amnya khusus untuk satu seni bina GPU?
   • Kerana ia disulitkan ke nombor siri GPU itu
   • Kerana NVIDIA melesenkannya setiap peranti
   • Kerana ia menyimpan data latihan di dalam enjin
   • Kerana penalaan automatik kernel membakar dalam kernel terpantas untuk susun atur memori dan teras tepat GPU tersebut
5. Ciri TensorRT-LLM yang manakah secara khusus membantu menyediakan model bahasa besar dengan cekap?
   • Batching dalam penerbangan (berterusan) dan cache KV halaman
   • Pembesaran imej automatik
   • Pengehosan web terbina dalam
   • Pembatalan bunyi audio
6. Why evaluate task accuracy after choosing lower-precision TensorRT execution?
   • Lower precision always preserves every output bit
   • Only the model filename affects predictions
   • Reduced numerical precision can change model outputs or quality
   • Accuracy evaluation is needed only during tokenization
7. A TensorRT dynamic-shape engine receives input outside its configured profile range. What should deployment validation check?
   • Whether the engine can accept every shape without a profile
   • Only whether the model name is short
   • Whether training can restart from a screenshot
   • Whether the profile supports that requested shape
8. A TensorRT engine is moved to a different runtime and GPU configuration. What must the team establish?
   • That any serialized engine runs unchanged everywhere
   • That the selected compatibility settings support the new environment
   • That the engine contains all its original training data
   • That every GPU shares one serial number