PR #25202 llama: fix quantized kv-cache for dsv4

llama: fix quantized kv-cache for dsv4 #25202

am17an merged 2 commits into ggml-org:master from am17an:dsv4-quant-kv-cahce

llama: fix quantized kv-cache for dsv4

14bb7ae0

am17an requested a review from

CISC 5 days ago

am17an requested a review from

ggerganov 5 days ago

am17an requested a review from

fairydreaming 5 days ago

github-actions added model

fairydreaming commented on 2026-07-01

remove GGML_PAD

33dea0b9

fairydreaming approved these changes on 2026-07-07

am17an added merge ready

ggerganov approved these changes on 2026-07-07

am17an merged 024c46ae into master 11 minutes ago

Reviewers

ggerganov

fairydreaming

CISC

Assignees

No one assigned

Labels

model merge ready

Milestone

No milestone