opencl: fix leak in Adreno q8_0 path#21212
Merged
max-krasnyansky merged 1 commit intoggml-org:masterfrom Apr 1, 2026
Merged
Conversation
max-krasnyansky
approved these changes
Apr 1, 2026
ggerganov
approved these changes
Apr 1, 2026
slartibardfast
pushed a commit
to slartibardfast/llama.cpp
that referenced
this pull request
Apr 12, 2026
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
There is a leak in Adreno q8_0 GEMM path. In particular, a subbuffer and an image1d_buffer were not released after transposing the activation.
This has little impact on Linux based systems, but causes considerable slow down on Windows (Adreno Windows driver seems extremely sensitive to the cumulation of outstanding CL objects). It also causes big discrepancy between tg number reported by llama-bench and llama-completion for q8_0 on Windows.
Requirements