Clean up per-thread parameter buffer pool and job submission logic#19772
Merged
reeselevine merged 18 commits intoggml-org:masterfrom Mar 2, 2026
Merged
Clean up per-thread parameter buffer pool and job submission logic#19772reeselevine merged 18 commits intoggml-org:masterfrom
reeselevine merged 18 commits intoggml-org:masterfrom
Conversation
github-actions
Bot
added
the
ggml
reeselevine
reviewed
Mar 2, 2026
Contributor
reeselevine
left a comment
reeselevine
left a comment
There was a problem hiding this comment.
Thanks, this looks good, and I think the heuristic for max param buffer pool size is reasonable.
reeselevine
approved these changes
Mar 2, 2026
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
…sion logic (ggml-org#19772) * Allow webgpu_buf_pool to resize if needed, remove inflight_threads, and replace inflight_threads with num_kernels for submission * Run clang-format * Keep track of num batched kernels that have not been submitted yet * Run clang-format * Increase buf pool max size * Increase param buf pool init size * Remove webgpu buf pool resizing * Merge with master * Add buffer pool growth * Move buffer pool growth outside of lock * Reduce max pool size to 32 * Run clang-format * Only resize param buf pool
Ethan-a2
pushed a commit
to Ethan-a2/llama.cpp
that referenced
this pull request
Mar 20, 2026
…sion logic (ggml-org#19772) * Allow webgpu_buf_pool to resize if needed, remove inflight_threads, and replace inflight_threads with num_kernels for submission * Run clang-format * Keep track of num batched kernels that have not been submitted yet * Run clang-format * Increase buf pool max size * Increase param buf pool init size * Remove webgpu buf pool resizing * Merge with master * Add buffer pool growth * Move buffer pool growth outside of lock * Reduce max pool size to 32 * Run clang-format * Only resize param buf pool
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…sion logic (ggml-org#19772) * Allow webgpu_buf_pool to resize if needed, remove inflight_threads, and replace inflight_threads with num_kernels for submission * Run clang-format * Keep track of num batched kernels that have not been submitted yet * Run clang-format * Increase buf pool max size * Increase param buf pool init size * Remove webgpu buf pool resizing * Merge with master * Add buffer pool growth * Move buffer pool growth outside of lock * Reduce max pool size to 32 * Run clang-format * Only resize param buf pool
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
…sion logic (ggml-org#19772) * Allow webgpu_buf_pool to resize if needed, remove inflight_threads, and replace inflight_threads with num_kernels for submission * Run clang-format * Keep track of num batched kernels that have not been submitted yet * Run clang-format * Increase buf pool max size * Increase param buf pool init size * Remove webgpu buf pool resizing * Merge with master * Add buffer pool growth * Move buffer pool growth outside of lock * Reduce max pool size to 32 * Run clang-format * Only resize param buf pool
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.
After splitting per-thread state and execution, this is the final cleanup diff.
We allow the buffer pool to grow in case of multiple kernels in a command requiring more buffers, remove the inflight_threads logic, and replace it with num_kernels to decide when to submit a batch of commands.