vulkan: Catch Vulkan C++ exceptions. #50
Merged
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
Don't crash when Vulkan exceptions occur during queue submission in graph_compute. Exit gracefully by returning GGML_STATUS_FAILED. Give up in case of vk::DeviceLostError, try to continue on other errors.
gianni-cor
merged commit 0cf1ef7
into
tetherto:temp-latest-finetuning
36 of 47 checks passed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This patch enables C++ exception handling for queue submission in the Vulkan backend.
Currently the Vulkan.hpp API produces C++ exceptions when other results than
VK_SUCCESSare returned.Since they do not occur in a try/catch block, the backend causes aborts / crashes in these cases.
This patch catches Vulkan exceptions (
vk::SystemError) inggml_vk_compute_forward, where only thevk::DeviceLostErroris handled as fatal error and others are only printed.It enables applications to exit gracefully by correctly returning
GGML_STATUS_FAILEDinggml_backend_vk_graph_computeinstead of aborting.