mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-16 21:00:14 +00:00
16d7f55193
in LoRA code, it will use conv1d to do projection for qkv, while the conv1d calculation is mathematically equivalent to matmul, and matmul is much faster than conv1d. The subsitution of the graph optimizer is: 1 conv1d >> 2 split + 1 squeeze + group_num matmul + 1 concat with this optimizer, we see 10%+ in one 1P model |
||
|---|---|---|
| .. | ||
| orttraining | ||
| pytorch_frontend_examples | ||
| tools | ||