Kimi Linear fix conv state update#19531
Merged
CISC merged 95 commits intoggml-org:masterfrom Feb 13, 2026
Merged
Conversation
…t for faster inference. sync'd to b7682
…near sync to latest
Member
Please take this out again and make this a purely bugfix PR. The block implementation can be done in a separate PR, however it's worth noting that there are several incoming improvements to this in #19375 that can be applied here also. |
Contributor
Author
|
Now only fix conv state update. |
CISC
approved these changes
Feb 13, 2026
liparetejas
pushed a commit
to liparetejas/llama.cpp
that referenced
this pull request
Feb 23, 2026
* fix conv state update for llama-server parallel serving --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
* fix conv state update for llama-server parallel serving --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
* fix conv state update for llama-server parallel serving --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Make sure to read the contributing guidelines before submitting a PR
The current implementation has incorrect conv state update such that it has state corruption when running parallel in llama-server. This is fixed in this PR.
This PR also includes the block implementation that speeds up 20% pp and VRAM saving.