Skip to content

model : fix MTP context kv cache allocation for deepseek2, glm4moe, c… - #28630

Open
LoganChu wants to merge 2 commits into
ggml-org:masterfrom
LoganChu:mtp-nextn-layer-filter
Open

model : fix MTP context kv cache allocation for deepseek2, glm4moe, c…#28630
LoganChu wants to merge 2 commits into
ggml-org:masterfrom
LoganChu:mtp-nextn-layer-filter

Commits

Commits on Sep 9, 2026