You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "makaveli10 (via GitHub)" <gi...@apache.org> on 2023/06/13 10:12:14 UTC

[GitHub] [tvm] makaveli10 opened a new issue, #15087: [Bug] ```from_onnx``` Gather op segmentation fault

makaveli10 opened a new issue, #15087:
URL: https://github.com/apache/tvm/issues/15087

   
   ### Environment
   
   Ubuntu 20.04
   
   ### Steps to reproduce
   
   ```tvmc tune --target "cuda" --output autotune.json encoder_model.onnx```
   
   For the gather op I see a segmentation fault in ```relay.frontend.from_onnx``` [on line](https://github.com/apache/tvm/blob/6c6ad6c43ad3cb378866683ed322316b173267aa/python/tvm/relay/frontend/onnx.py#L7052). Which calls ```fold_constant()``` on this node ```less(0i64 /* span=/layers.0/self_attn/Gather./layers.0/self_attn/Constant_output_0:0:0 */, 0i64)```:
   ```
   op_name = Gather,
   attrs: {'axis': 0, 'tvm_custom': {'name': '/layers.0/self_attn/Gather', 'num_outputs': 1}}
   less(0i64 /* span=/layers.0/self_attn/Gather./layers.0/self_attn/Constant_output_0:0:0 */, 0i64)
   ```
   
   
   ### Triage
   
   Please refer to the list of label tags [here](https://github.com/apache/tvm/wiki/Issue-Triage-Labels) to find the relevant tags and add them below in a bullet format (example below).
   
   * needs-triage
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


Re: [I] [Bug] ```from_onnx``` Gather op segmentation fault [tvm]

Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen closed issue #15087: [Bug] ```from_onnx``` Gather op segmentation fault
URL: https://github.com/apache/tvm/issues/15087


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


[GitHub] [tvm] quic-sanirudh commented on issue #15087: [Bug] ```from_onnx``` Gather op segmentation fault

Posted by "quic-sanirudh (via GitHub)" <gi...@apache.org>.
quic-sanirudh commented on issue #15087:
URL: https://github.com/apache/tvm/issues/15087#issuecomment-1602688597

   Could you provide a small test case to reproduce this issue locally. Perhaps a small onnx model that contains just the subgraph including the gather op?
   
   P.S. I've found the [onnx-modifier](https://github.com/ZhangGe6/onnx-modifier) tool to be very useful to create small subgraphs for test cases in onnx. Or if you could share the whole model, that should also be fine.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org