Repository navigation
ggml-meta: resolve multi buffer views - #29266
Merged
Merged
Conversation
github-actions
Bot
added
the
ggml
JohannesGaessler
approved these changes
Sep 22, 2026
JohannesGaessler
left a comment
JohannesGaessler
left a comment
Contributor
There was a problem hiding this comment.
These changes are I think okay and I probably would have done equivalent ones if I had known that it could be fixed like this. Please add a TODO to revisit the logic in the future if and when the memory allocation has been refactored.
pwilkin
approved these changes
Sep 22, 2026
pwilkin
left a comment
pwilkin
left a comment
Member
There was a problem hiding this comment.
If this can actually unlock most cases, then I think it's worth it.
pwilkin
approved these changes
Sep 22, 2026
ggerganov
approved these changes
Sep 22, 2026
1 task done
4 tasks
LadislavSopko
pushed a commit
to 0ics-srls/llama.cpp
that referenced
this pull request
Oct 5, 2026
* ggml-meta: resolve multi buffer views * add TODO to revisit if graph allocator gets refactored
frostyautumnleaf
pushed a commit
to frostyautumnleaf/llama.cpp
that referenced
this pull request
Oct 5, 2026
* ggml-meta: resolve multi buffer views * add TODO to revisit if graph allocator gets refactored
edwardyoon
pushed a commit
to edwardyoon/focus-llama
that referenced
this pull request
Oct 7, 2026
* ggml-meta: resolve multi buffer views * add TODO to revisit if graph allocator gets refactored (cherry picked from commit 9425611)
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This is the most minimal change I can come up with to unblock Vulkan tensor parallel. It resolves multi-buffers in views, which unblocks most cases with split model or kv tensors.
@JohannesGaessler I know you want a proper allocator change, but for the short time it would help us a lot to unblock the most common multi-buffer cases. I don't think this will interfere with a long term proper refactor.
Requirements