tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-08 00:12:44 -04:00
Code Issues Packages Projects Releases Wiki Activity
392 Commits 494 Branches 4,324 Tags
master-38de86a
Commit Graph

1 Commits

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