mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-15 01:23:42 +00:00
* Add micro-benchmarks for Attention and SkipLayerNormalization ops. * Add choices for argument provider and precision. * Automatically select CUDA or ROCM execution provider. |
||
|---|---|---|
| .. | ||
| models | ||
| attention.py | ||
| benchmark.py | ||
| fast_gelu.py | ||
| matmul.py | ||
| skip_layer_norm.py | ||