llama.cpp
CUDA: add dynamic shared mem to softmax, refactor general usage
#14497
Merged
Overview
Commits
3
Changes
View On GitHub
Commits
  • CUDA: add dynamic shared mem to softmax, refactor general usage
    am17an committed 166 days ago
  • Review: refactor switch statement, change cross_entropy to use full size
    am17an committed 166 days ago
  • rebase
    am17an committed 166 days ago
FAQ Terms Privacy Refunds Impressum
Loading