Mark Ward
|
63c763685f
log when the waiting for the process to stop to help debug when other tasks execute during this wait.
|
1 tahun lalu |
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 tahun lalu |
Daniel Hiltgen
|
d6e3b64582
Fix concurrency for CPU mode
|
1 tahun lalu |
Daniel Hiltgen
|
9b5a3c5991
Merge pull request #3914 from dhiltgen/mac_perf
|
1 tahun lalu |
Jeffrey Morgan
|
00b0699c75
Reload model if `num_gpu` changes (#3920)
|
1 tahun lalu |
Daniel Hiltgen
|
b123be5b71
Adjust context size for parallelism
|
1 tahun lalu |
Bryce Reitano
|
36a6daccab
Restructure loading conditional chain
|
1 tahun lalu |
Bryce Reitano
|
284e02bed0
Move ggml loading to when we attempt fitting
|
1 tahun lalu |
Daniel Hiltgen
|
34b9db5afc
Request and model concurrency
|
1 tahun lalu |