opencl: bugfix: missing increment of ref_count in ggml_backend_opencl_init() - #26162
Merged
Conversation
Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
github-actions
Bot
added
ggml
akleine
changed the title
lhez
approved these changes
Jul 31, 2026
max-krasnyansky
approved these changes
Jul 31, 2026
Contributor
|
Just as a note, this fixes a legacy API; now applications will likely go through the new backend API. But the fix does make sense. |
kashif
pushed a commit
to kashif/llama.cpp
that referenced
this pull request
Aug 2, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
TheTom
pushed a commit
to TheTom/llama-cpp-turboquant
that referenced
this pull request
Aug 3, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
belarusian
pushed a commit
to belarusian/llama.cpp
that referenced
this pull request
Aug 4, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
smalinin
pushed a commit
to smalinin/llama.cpp
that referenced
this pull request
Aug 4, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
satindergrewal
pushed a commit
to satindergrewal/llama.cpp
that referenced
this pull request
Aug 11, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
satindergrewal
pushed a commit
to satindergrewal/llama.cpp
that referenced
this pull request
Aug 12, 2026
…l-org#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result would be -1 here, and consequently, the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )
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
Add missing increment
ref_countinggml_backend_opencl_init()Compare the similar method
ggml_backend_opencl_device_init(), here we find the needed increment already.Additional information
This is important later in the
free()method ofggml_backend_opencl_contextat program end.If we do not increment the
ref_count, the result would be -1 here, and consequently, some parts offree()would not executed. For example the profiling data would not be flushed and written. ( #ifdef GGML_OPENCL_PROFILING )Requirements