Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
10,225 Commits 5 Branches 0 Tags
75587a05b39e5d5866a2e120178c75c12dfb75cb
Commit Graph
1 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Robert Esclapez e1a1abb787 ggml-cuda: Allow transpose-free gemmv computation (#26171) 
When matrix's weights are shaped 1xK is leverage a transpose-free
computation to use mat_mul_vec_f.
 2026-07-30 21:39:46 +08:00