llama.cpp
[SYCL] Fix FA mkl issue: a mask broadcast over heads or batches
#31536
Merged

Commits
  • fix the SYCL fa with mkl error of a mask broadcast over heads or batches; add argument cache-ram to start-svr.sh
    arthw committed 17 days ago
  • add argument cache-ram to win-start-svr.bat
    arthw committed 17 days ago
  • Merge branch 'master' into fix_fa_mkl_mask
    arthw committed 10 days ago
  • fix format issue, remove --cache-ram in script: move to another PR
    arthw committed 3 days ago
Loading