CLBlast: Fix temporary buffer size for f16 conversion (wsize) #3603
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
Fix buffer overflow. Reduce the size to fit just one 2D slice. Assert sufficient size.
KerfuffleV2
approved these changes
Oct 14, 2023
ggerganov
approved these changes
Oct 17, 2023
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Outdated suggestions cannot be applied.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.
In
ggml_cl_mul_mat_f16,wdatais used for conversion of bothsrc1anddst, but only the size ofsrc1was considered. Whendstrequired more space, it could lead to buffer overflow. Crashes reported in #2378 and #2736 may have been caused by this.For 3D and 4D tensors, the size to fit the whole
src1was requested, but only one 2D slice is processed at a time, so the requirement can be reduced.Tested with AddressSanitizer.