Conversation
Nexesenex
added a commit
to Nexesenex/ik_llama.cpp.nxs
that referenced
this pull request
Nov 6, 2025
This reverts commit fd3757d.
Nexesenex
added a commit
to Nexesenex/ik_llama.cpp.nxs
that referenced
this pull request
Nov 6, 2025
This reverts commit fd3757d.
ikawrakow
pushed a commit
that referenced
this pull request
Nov 11, 2025
ikawrakow
added a commit
that referenced
this pull request
Nov 11, 2025
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR derives from PR 16847 in mainline.
On my GPU (RTX-4080) it is a very minor improvement over the main branch (~0.5% better TG for GPT-OSS-20B-MXFP4, less for other models). But based on the discussion in the mainline PR, it may lead to larger performance gains for low memory bandwidth GPUs.
The PR also adds the
-mmvq | --merge-qkvoption (see #878) tollama-bench.