ggml: add logical worker lanes for trace profiling#13
Merged
alex-spacemit merged 1 commit intoJul 2, 2026
Merged
Conversation
Wire ggml-profile into the ggml build behind GGML_BUILD_PROFILE and enable CPU operator trace events. Emit operator begin/end events from each compute worker, using stable logical trace lanes (pid=2, tid=ith) named ggml-worker-N instead of Linux OS TIDs. This makes GGML_TRACE=1 produce per-worker operator profiles that match the configured compute thread count, especially when using a persistent threadpool such as llama-bench.
co-seven
force-pushed
the
profile-trace-workers
branch
from
99d6ec7 to
e7a4081
Compare
alex-spacemit
merged commit 9c370db
into
spacemit-com:spacemit-mtmd
10 of 11 checks passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Wire ggml-profile into the ggml build behind GGML_BUILD_PROFILE and
enable CPU operator trace events. Emit operator begin/end events from
each compute worker, using stable logical trace lanes (pid=2, tid=ith)
named ggml-worker-N instead of Linux OS TIDs.
This makes GGML_TRACE=1 produce per-worker operator profiles that match
the configured compute thread count, especially when using a persistent
threadpool such as llama-bench.