vulkan: throw system error instead of SIGABRT during init on older devices #16156
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
github-actions
bot
added
Vulkan
yael-works
pushed a commit
to yael-works/llama.cpp
that referenced
this pull request
Oct 15, 2025
…vices (ggml-org#16156) * Throw system error on old Vulkan driver rather than SIGABRT * Optionally handle any potential error in vulkan init
pwilkin
pushed a commit
to pwilkin/llama.cpp
that referenced
this pull request
Oct 23, 2025
…vices (ggml-org#16156) * Throw system error on old Vulkan driver rather than SIGABRT * Optionally handle any potential error in vulkan init
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Outdated suggestions cannot be applied.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.
Fixes #16142
Main issue is
llama_supports_gpu_offloadshould not get SIGABRT if backend can't initialize correctly inggml_vk_instance_init. System error will make sure it is not added to registry anyway.Optionally, added catches in
ggml_backend_vk_regto returnnullfor any errors, unless this was intended to be handled upstream. In that case i can remove that commit.