引導式測驗 · 硬 等級
torch.compile 與 PyTorch 2 圖形編譯測驗
了解 torch.compile 擷取和後端角色、圖形中斷、編譯開銷、形狀專業化和公平效能檢查。
問題 1 的 8
What does torch.compile attempt to do with compatible PyTorch computation?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- What does torch.compile attempt to do with compatible PyTorch computation?
- Rewrite the model’s training labels
- Guarantee the same speedup for every workload
- Capture and compile compatible tensor operations for optimized execution
- Replace the model’s objective function
- Which component commonly captures Python frames in PyTorch 2 compilation?
- TorchInductor
- TorchDynamo
- TorchScript
- 自動梯度
- What does TorchInductor commonly provide?
- Python frame and graph capture
- Optimizer state management
- Data batching and shuffling
- A compiler backend that generates optimized code
- Why can the first compiled call be slower than eager execution?
- Tracing and compilation add work to the first call
- The first call always uses a larger training batch
- Graph capture removes GPU operations
- The first output is not computed
- With the default partial-graph behavior, what can happen when part of execution cannot be captured?
- The entire model necessarily raises an error
- An uncaptured region may run eagerly before capture resumes
- The unsupported operation is omitted from the output
- The optimizer changes the learning rate automatically
- What can happen when input shapes change?
- A guard failure may trigger another specialized compilation
- All shapes are padded to one size automatically
- The compiled model ignores future input shapes
- A new dataset is created for each shape
- How should a team assess a claimed compile speedup?
- Time only the first call and call it steady state
- Ignore data loading and synchronization
- Use different models and batches in each measurement
- Compare warmed-up end-to-end performance on representative inputs
- What should be checked after enabling compilation for training?
- Output and gradient agreement with eager execution
- The compile log contains no warnings
- Warm throughput is higher than eager mode
- Peak memory is lower than eager mode