mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-07 17:15:29 +00:00
### Description This PR provides a vectorized algorithm for NHWC GroupedConv to improve performance. The aggregate time of GroupedConv in mobilenetv2-12 becomes ~1ms from ~4ms on Intel Alder Lake machine. About 20% improvement for the whole model. |
||
|---|---|---|
| .. | ||
| ops | ||
| attribute-with-cache-key.ts | ||
| gpu-data-manager.ts | ||
| op-resolve-rules.ts | ||
| program-manager.ts | ||
| types.ts | ||