Fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32#1454
Merged
ggerganov merged 4 commits intoggml-org:masterfrom May 14, 2023
Merged
Conversation
memcpy needs to be synchronized across threads to avoid race conditions. => do it in INIT phase
Member
|
I already made a fix for this in #1450 But will use your version as it is less hacky |
Member
|
Resolve the CI error + conflict and will merge it |
Collaborator
Author
|
Oh didnt see that commit with the fixes. Trailing whitespace removed. Do you resolve the conflict or should I? |
ggerganov
reviewed
May 14, 2023
ggerganov
approved these changes
May 14, 2023
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…pute_forward_diag_mask_f32 (ggml-org#1454) * fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 memcpy needs to be synchronized across threads to avoid race conditions. => do it in INIT phase * remove trailing whitespace * Update ggml.c --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
phuongncn
pushed a commit
to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4
that referenced
this pull request
Apr 28, 2026
…pute_forward_diag_mask_f32 (ggml-org#1454) * fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 memcpy needs to be synchronized across threads to avoid race conditions. => do it in INIT phase * remove trailing whitespace * Update ggml.c --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
phuongncn
pushed a commit
to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4
that referenced
this pull request
Apr 28, 2026
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
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.
test-grad0.c catched a bug in ggml_compute_forward_diag_mask_f32 when running in threaded mode.
This only affects non-inplace occurences of diag_mask.
memcpy needs to be synchronized across threads to avoid race conditions, so just do it in INIT phase.
Use memcpy instead of the dup function, because the dup function just returns in INIT phase.