 Patrick Devine
|
4cc3be3035
Move envconfig and consolidate env vars (#4608)
|
11 ماه پیش |
 Sang Park
|
4434d7f447
Correct typo in error message (#4535)
|
11 ماه پیش |
 Daniel Hiltgen
|
ec231a7923
Remove VRAM convergence check for windows
|
11 ماه پیش |
|
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
11 ماه پیش |
|
Daniel Hiltgen
|
4142c3ef7c
Always use the sorted list of GPUs
|
11 ماه پیش |
 Jeffrey Morgan
|
bb6fd02298
Don't clamp ctx size in `PredictServerFit` (#4317)
|
11 ماه پیش |
|
Daniel Hiltgen
|
354ad9254e
Wait for GPU free memory reporting to converge
|
11 ماه پیش |
|
Jeffrey Morgan
|
c9f98622b1
Skip scheduling cancelled requests, always reload unloaded runners (#4189)
|
1 سال پیش |
|
Jeffrey Morgan
|
dfa2f32ca0
unload in critical section (#4187)
|
1 سال پیش |
|
Daniel Hiltgen
|
f56aa20014
Centralize server config handling
|
1 سال پیش |
|
Jeffrey Morgan
|
942c979232
allocate a large enough kv cache for all parallel requests (#4162)
|
1 سال پیش |
|
Daniel Hiltgen
|
20f6c06569
Make maximum pending request configurable
|
1 سال پیش |
 Mark Ward
|
63c763685f
log when the waiting for the process to stop to help debug when other tasks execute during this wait.
|
1 سال پیش |
|
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 سال پیش |
|
Daniel Hiltgen
|
d6e3b64582
Fix concurrency for CPU mode
|
1 سال پیش |
 Daniel Hiltgen
|
9b5a3c5991
Merge pull request #3914 from dhiltgen/mac_perf
|
1 سال پیش |
|
Jeffrey Morgan
|
00b0699c75
Reload model if `num_gpu` changes (#3920)
|
1 سال پیش |
|
Daniel Hiltgen
|
b123be5b71
Adjust context size for parallelism
|
1 سال پیش |
 Bryce Reitano
|
36a6daccab
Restructure loading conditional chain
|
1 سال پیش |
|
Bryce Reitano
|
284e02bed0
Move ggml loading to when we attempt fitting
|
1 سال پیش |
|
Daniel Hiltgen
|
34b9db5afc
Request and model concurrency
|
1 سال پیش |
