Home Explore Help
Sign In
cturan
/
llama.cpp
mirror of https://github.com/cturan/llama.cpp
1
0
Fork 0
Files Issues 0 Wiki
Browse Source

CUDA: lower GPU latency + fix Windows performance (#3110)

Johannes Gäßler 2 years ago
parent
1b0d09259e
commit
d54a4027a6
1 changed files with 468 additions and 504 deletions
Split View Show Diff Stats
  1. 468 504
      ggml-cuda.cu

File diff suppressed because it is too large
+ 468 - 504
ggml-cuda.cu


Some files were not shown because too many files changed in this diff