llama.cpp
Add preemptive priority scheduling
#22851
Closed
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
10
Changes
View On
GitHub
Add preemptive priority scheduling
#22851
lowlyocean
wants to merge 10 commits into
ggml-org:master
from
lowlyocean:unload_priority
Remove sleeping before adding priority scheduling
0d99e064
Add preemptive priority scheduling to router mode
61da93e0
Fix new methods declared inside unload_lru() instead of as standalone…
f481f684
Fix bad_function_call bug
087eb36a
OK- priority is respected
653a0b31
Add --models-idle-timeout to replace old --sleep-idle-seconds flag
9349beb1
lowlyocean
changed the title
Feature Request: [Router mode] Preemptive Priority scheduling
Add preemptive priority scheduling
40 days ago
github-actions
added
server/webui
github-actions
added
examples
github-actions
added
python
github-actions
added
server
Do not reset idle timer for /metrics, /models, /props, /health
68ad4509
Cleanup logs and documentation
a359e8eb
Merge branch 'master' into unload_priority
f401f4de
lowlyocean
marked this pull request as ready for review
37 days ago
lowlyocean
requested a review
37 days ago
lowlyocean
requested a review
37 days ago
lowlyocean
requested a review
37 days ago
Merge branch 'master' into unload_priority
46f63a22
ngxson
closed this
36 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
No reviews
Assignees
No one assigned
Labels
server/webui
examples
python
server
Milestone
No milestone
Login to write a write a comment.
Login via GitHub