summaryrefslogtreecommitdiff
path: root/ggml-cuda/quantize.cuh
AgeCommit message (Expand)Author
2024-06-09CUDA: revise q8_1 data layout for mul_mat_q (#7824)Johannes Gäßler
2024-04-09llama : add Command R Plus support (#6491)Carolinabanana
2024-03-25cuda : refactor into multiple files (#6269)slaren