Skip to content

Skip node output dump for MemcpyToHost - #25651

Merged
kunal-vaishnavi merged 1 commit into
mainfrom
tlwu/skip_dump_MemcpyToHost
Aug 8, 2025
Merged

kunal-vaishnavi merged 1 commit into
mainfrom
tlwu/skip_dump_MemcpyToHost

Conversation

@tianleiwu

Copy link
Copy Markdown
Contributor

Fix node output dump for MemcpyToHost. The statistics data is not correct, since data might not be copied to CPU yet:

MemcpyToHost node: Memcpy_token_232
Input 0 Name: /model/layers.6/moe/router/Add/output_0_CUDAExecutionProvider
 Shape: {1,1,32}
OrtMemoryInfo:[name:Cuda OrtMemType:0 OrtAllocatorType:1 Device:[DeviceType:1 MemoryType:0 VendorId:4318 DeviceId:0 Alignment:0]]
Min=-2.5136719,Max=1.6914062
-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
Min=-4888,Max=6672,NaN=2

This fix will skip the output dump (or statistics) like

-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
 is same as input

@tianleiwu

Copy link
Copy Markdown
Contributor Author

/azp run Windows x64 QNN CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@kunal-vaishnavi
kunal-vaishnavi merged commit 067b154 into main Aug 8, 2025
@kunal-vaishnavi
kunal-vaishnavi deleted the tlwu/skip_dump_MemcpyToHost branch August 8, 2025 01:48
Sanket Kale (sanketkaleoss) pushed a commit to sanketkaleoss/onnxruntime that referenced this pull request Aug 11, 2025
Fix node output dump for MemcpyToHost. The statistics data is not
correct, since data might not be copied to CPU yet:

```
MemcpyToHost node: Memcpy_token_232
Input 0 Name: /model/layers.6/moe/router/Add/output_0_CUDAExecutionProvider
 Shape: {1,1,32}
OrtMemoryInfo:[name:Cuda OrtMemType:0 OrtAllocatorType:1 Device:[DeviceType:1 MemoryType:0 VendorId:4318 DeviceId:0 Alignment:0]]
Min=-2.5136719,Max=1.6914062
-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
Min=-4888,Max=6672,NaN=2
```

This fix will skip the output dump (or statistics) like
```
-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
 is same as input
```
Maximilian Müller (gedoensmax) pushed a commit to gedoensmax/onnxruntime that referenced this pull request Sep 2, 2025
Fix node output dump for MemcpyToHost. The statistics data is not
correct, since data might not be copied to CPU yet:

```
MemcpyToHost node: Memcpy_token_232
Input 0 Name: /model/layers.6/moe/router/Add/output_0_CUDAExecutionProvider
 Shape: {1,1,32}
OrtMemoryInfo:[name:Cuda OrtMemType:0 OrtAllocatorType:1 Device:[DeviceType:1 MemoryType:0 VendorId:4318 DeviceId:0 Alignment:0]]
Min=-2.5136719,Max=1.6914062
-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
Min=-4888,Max=6672,NaN=2
```

This fix will skip the output dump (or statistics) like
```
-----------
Output 0 Name: /model/layers.6/moe/router/Add/output_0
 Shape: {1,1,32}
 is same as input
```
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants