Skip to content

CUDA: add gqa_ratio 4 for GLM 4.7 flash#18953

Merged
am17an merged 6 commits intoggml-org:masterfrom
am17an:glm_4.7_headsize
Jan 22, 2026
Merged

CUDA: add gqa_ratio 4 for GLM 4.7 flash#18953
am17an merged 6 commits intoggml-org:masterfrom
am17an:glm_4.7_headsize

Commits

Commits on Jan 20, 2026

Commits on Jan 21, 2026