llama : enforce the same K and V cache types for DeepSeek V4; enable FA if V cache is quantized#25871
Open
fairydreaming wants to merge 1 commit into
Open
llama : enforce the same K and V cache types for DeepSeek V4; enable FA if V cache is quantized#25871fairydreaming wants to merge 1 commit into
fairydreaming wants to merge 1 commit into
Conversation
…FA if V cache is quantized
fairydreaming
commented
Jul 18, 2026
| } | ||
| } | ||
|
|
||
| if (model->arch == LLM_ARCH_DEEPSEEK4 && params.type_k != params.type_v) { |
Collaborator
Author
There was a problem hiding this comment.
I think this currently applies also to DeepSeek V3.2 and models where hparams.is_mla() is true since they use a view of K cache as V cache, maybe it's worth extending the condition?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
This PR fixes issue described in detail here. It does it by:
Fixes #25851
Requirements