Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-10-31 15:10:16 +01:00
Code Issues Packages Projects Releases Wiki Activity
3,131 Commits 335 Branches 2,573 Tags 319 MiB
148995e5e5
Commit Graph

251 Commits

Author SHA1 Message Date
slaren
02d6988121
Improve cuBLAS performance by dequantizing on the GPU (#1065) 2023-04-20 03:14:14 +02:00