Tutorial: Benchmarking FlashInfer Kernels
This tutorial shows you how to accurately benchmark FlashInfer kernels.
Goal
Measure the performance of FlashInfer kernels:
- Get accurate GPU kernel execution time
- Compare multiple backends (FlashAttention2/3, cuDNN, CUTLASS, TensorRT-LLM)
- Generate reproducible benchmark results
- Save results to CSV for analysis
Timing Methods
FlashInfer supports two timing methods:
- CUPTI (Preferred): Hardware-level profiling for most accurate
[Description truncada. Veja o README completo no GitHub.]