llama.cpp
ggml : add CPU TurboQuant KV cache types (TBQ3_0 / TBQ4_0)
#21089

Open

ggml : add CPU TurboQuant KV cache types (TBQ3_0 / TBQ4_0) #21089

elusznik wants to merge 3 commits into ggml-org:master from elusznik:turboquant-cpu-tbq-pr

feat: add CPU TurboQuant KV cache types

d5a71640

ggml : limit the first TurboQuant CPU PR to TBQ

f96df927

github-actions added testing

github-actions added examples

github-actions added server

github-actions added ggml

elusznik marked this pull request as ready for review 5 days ago

elusznik requested a review 5 days ago

elusznik requested a review from

ggerganov 5 days ago

elusznik requested a review from

ngxson 5 days ago

elusznik requested a review from

CISC 5 days ago

elusznik requested a review 5 days ago

elusznik requested a review from

copilot-pull-request-reviewer 5 days ago

copilot-pull-request-reviewer commented on 2026-03-28

ggml : fix TurboQuant CPU review issues

0aae7d78

Reviewers

ggerganov

ngxson

CISC

Assignees

No one assigned

Labels

testing examples server ggml

Milestone

No milestone