llama: fix leaked buffers for mmap + split files #16765
Open
+16
−10
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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 #16762 . As correctly pointed out by Aman, the problem is that the pointer to the buffer is being overwritten when looping over the split files. As a consequence the backend buffers are currently being leaked.
More generally, for the combination of mmap and split files there can be more than one backend buffer being associated with a ggml context which wasn't being correctly represented by the type
vector<pair<ggml_context_ptr, ggml_buffer_ptr>>. I changed the type tovector<pair<ggml_context_ptr, vector<ggml_buffer_ptr>>>instead.