llama.cpp
webui: auto-refresh /props on inference start to resync model metadata
#16784

Merged

webui: auto-refresh /props on inference start to resync model metadata #16784

allozaur merged 6 commits into ggml-org:master from ServeurpersoCom:webui-props-auto-refresh

ServeurpersoCom requested a review from

allozaur 50 days ago

github-actions added examples

github-actions added server

ServeurpersoCom force pushed 50 days ago

ServeurpersoCom marked this pull request as draft 50 days ago

ServeurpersoCom marked this pull request as ready for review 49 days ago

ServeurpersoCom closed this 45 days ago

ServeurpersoCom force pushed to 8da3c0e2 45 days ago

ServeurpersoCom reopened this 45 days ago

allozaur approved these changes on 2025-10-28

ServeurpersoCom force pushed 45 days ago

webui: auto-refresh /props on inference start to resync model metadata

7f4dfb21

fix: restore proper legacy behavior in webui by using unified /props …

4e2a00e5

fix: detect first valid SSE chunk and refresh server props once

a2f6661c

fix: removed the slots availability throttle constant and state

dbae892f

webui: purge ai-generated cruft

b9747cca

ServeurpersoCom force pushed to b9747cca 44 days ago

chore: update webui static build

d2af7f02

allozaur merged 2f68ce7c into master 44 days ago

Reviewers

allozaur

Assignees

No one assigned

Labels

examples server

Milestone

No milestone