CUDA: lower GPU latency + fix Windows performance
This commit is contained in:
parent
ec2a24fedf
commit
9268745025
1 changed files with 572 additions and 608 deletions
1008
ggml-cuda.cu
1008
ggml-cuda.cu
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue