add cuda debugging blogpost #66
Merged
+348
−0
Conversation
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
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Deploying vllm-blog-source with
|
| Latest commit: |
e77d1bb
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://24502232.vllm-blog-source.pages.dev |
| Branch Preview URL: | https://cuda-debugging.vllm-blog-source.pages.dev |
Signed-off-by: youkaichao <[email protected]>
_posts/2025-08-11-cuda-debugging.md
Outdated
|
|
||
| > Additionally, the documentation states that enabling `CUDA_ENABLE_COREDUMP_ON_EXCEPTION=1` not only enables CUDA core dump but also generates a CPU coredump by default. However, in practice, we find that the CPU coredump contains little useful information and is difficult to analyze. | ||
|
|
||
| > If you want live data for debugging, you can also enable `CUDA_DEVICE_WAITS_ON_EXCEPTION=1` environment variable, which does not use CUDA core dump, but stops GPU execution immediately when an exception occurs, and hangs there, waiting for users to attach a debugger (like cuda-gdb) to inspect the GPU state, where the full GPU memory is still intact. However, this approach is less automatic and requires more manual intervention. |
There was a problem hiding this comment.
nice! happy to see this pointed out too; super useful!
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
_posts/2025-08-11-cuda-debugging.md
Outdated
| Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. | ||
| ``` | ||
|
|
||
| The error message suggests adding `CUDA_LAUNCH_BLOCKING=1` when running the code. However, there are still two problems: |
There was a problem hiding this comment.
Suggested change
| The error message suggests adding `CUDA_LAUNCH_BLOCKING=1` when running the code. However, there are still two problems: | |
| The challenging bit here is: | |
| > CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. | |
| In our experience the python stack traces for these types of exceptions are basically always incorrect and pretty worthless. To resolve this the error message suggests adding `CUDA_LAUNCH_BLOCKING=1` when running the code. However, there are still two problems: |
LucasWilkinson
approved these changes
Aug 12, 2025
Signed-off-by: youkaichao <[email protected]>
Signed-off-by: youkaichao <[email protected]>
Thanks for helping to improve the doc! Added you in the last. |
Signed-off-by: youkaichao <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.