Historia zmian

Autor SHA1 Wiadomość Data
  Mark Ward 63c763685f log when the waiting for the process to stop to help debug when other tasks execute during this wait. 1 rok temu
  Mark Ward f4a73d57a4 fix runner expire during active use. Clearing the expire timer as it is used. Allowing the finish to assign an expire timer so that the runner will expire after no use. 1 rok temu
  Daniel Hiltgen d6e3b64582 Fix concurrency for CPU mode 1 rok temu
  Daniel Hiltgen 9b5a3c5991 Merge pull request #3914 from dhiltgen/mac_perf 1 rok temu
  Jeffrey Morgan 00b0699c75 Reload model if `num_gpu` changes (#3920) 1 rok temu
  Daniel Hiltgen b123be5b71 Adjust context size for parallelism 1 rok temu
  Bryce Reitano 36a6daccab Restructure loading conditional chain 1 rok temu
  Bryce Reitano 284e02bed0 Move ggml loading to when we attempt fitting 1 rok temu
  Daniel Hiltgen 34b9db5afc Request and model concurrency 1 rok temu