# Further Discussion from the issue written by @jdomkline

**URL:** <https://forum.opensearch.org/t/further-discussion-from-the-issue-written-by-jdomkline/23321>\
**Category:** k-NN\
**Tags:** troubleshoot\
**Created:** [February 5, 2025, 5:19am UTC](https://forum.opensearch.org/t/further-discussion-from-the-issue-written-by-jdomkline/23321 "2025-02-05T05:19:06Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![yeonghyeonKo](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/yeonghyeonko/32/8202_2.png) [@yeonghyeonKo](https://forum.opensearch.org/u/yeonghyeonKo)\
**Post date:** [February 5, 2025, 5:19am UTC](https://forum.opensearch.org/t/further-discussion-from-the-issue-written-by-jdomkline/23321/1 "2025-02-05T05:19:06Z")

</div>

**Versions** (relevant - OpenSearch/Dashboard/Server OS/Browser):  
2.15

**Describe the issue** :  
Since the original issue is closed and it no longer accepts new replies, I write this topic.

> [@Pretrained Model Download/Register Fails for TorchScript](https://forum.opensearch.org/t/pretrained-model-download-register-fails-for-torchscript/20577):
>
> Versions (relevant - OpenSearch/Dashboard/Server OS/Browser): Mac Sonoma 14.5 OS { “name”: “opensearch-node1”, “cluster\_name”: “opensearch-cluster”, “cluster\_uuid”: “\_Q9SlIo8RHirvzb-r0CkTA”, “version”: { “distribution”: “opensearch”, “number”: “2.15.0”, “build\_type”: “tar”, “build\_hash”: “61dbcd0795c9bfe9b81e5762175414bc38bbcadf”, “build\_date”: “2024-06-20T03:27:32.562036890Z”, “build\_snapshot”: false, “lucene\_version”: “9.10.0”, “minimum\_wire\_compatibility\_version”: “7.10.0”, “m…

```auto
Failed to deploy model 0UZj05QBIjmJRhPKICkD

ai.djl.engine.EngineException:
Unknown builtin op: aten::scaled_dot_product_attention.
Here are some suggestions:
	aten::_scaled_dot_product_attention

The original call is:
  File "code/ __torch__ /transformers/models/bert/modeling_bert/___torch_mangle_8118.py", line 38
    x1 = torch.view(_10, [_12, int(_13), 12, 64])
    value_layer = torch.permute(x1, [0, 2, 1, 3])
    attn_output = torch.scaled_dot_product_attention(query_layer, key_layer, value_layer, attention_mask)
                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
    attn_output0 = torch.transpose(attn_output, 1, 2)
    input = torch.reshape(attn_output0, [_0, _1, 768])
	at ai.djl.pytorch.jni.PyTorchLibrary.moduleLoad(Native Method) ~[pytorch-engine-0.28.0.jar:?]

```

I found the similar issue in Github and one of the comments from this says (link: [RuntimeError: Unknown builtin op: aten::scaled\_dot\_product\_attention. · Issue #134 · YuliangXiu/ECON · GitHub](https://github.com/YuliangXiu/ECON/issues/134#issuecomment-2399613955)):

> You shouldn’t use PyTorch 1.13.1; you need at least PyTorch 2.0 or higher because the scaled\_dot\_product\_attention function is only available in version 2.0. Additionally, you need to update your CUDA and PyTorch3D versions so that they are compatible with each other, and that should fix the issue.

---

<div class="post-metadata">

**Author:** ![yeonghyeonKo](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/yeonghyeonko/32/8202_2.png) [@yeonghyeonKo](https://forum.opensearch.org/u/yeonghyeonKo)\
**Post date:** [February 5, 2025, 5:19am UTC](https://forum.opensearch.org/t/further-discussion-from-the-issue-written-by-jdomkline/23321/2 "2025-02-05T05:19:26Z")

</div>

@jdomkline

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex019/uploads/mauve_hedgehog/original/2X/3/33547ea01a5b12dcca2958411d3edd97ae2ea8c1.png) [@system](https://forum.opensearch.org/u/system)\
**Post date:** [April 6, 2025, 5:20am UTC](https://forum.opensearch.org/t/further-discussion-from-the-issue-written-by-jdomkline/23321/3 "2025-04-06T05:20:02Z")

</div>

Closed on April 6, 2025, 5:20am UTC

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.