Ohad Ravid ohadravid
ohadravid
/ min_repro.py
Last active
January 22, 2025 09:15
A script for comparing the TensorRT compilation of torch's `scaled_dot_product_attention`, `multi_head_attention_forward` and an explicit version
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import io | |
| import tensorrt as trt | |
| import torch_tensorrt | |
| class AttentionUsingScaledDotProduct(nn.Module): | |
| """ |