llama.cpp
server: allow accessing /metrics and /slots during llama_decode()
#27041
Merged

server: allow accessing /metrics and /slots during llama_decode() #27041

ngxson merged 6 commits into master from xsn/non_blocking_metrics
ngxson
ngxson server_queue::worker
fca17612
ngxson call llama_decode inside yield_to_queue
0b42458e
github-actions github-actions added server
ngxson also handle process_mtmd_chunk
a35d2af1
ngxson clean up
d809c0f3
ngxson nits
98e489eb
ngxson ngxson marked this pull request as ready for review 1 day ago
ngxson ngxson requested a review 1 day ago
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-08-14
ServeurpersoCom
ggerganov
ggerganov approved these changes on 2026-08-14
ngxson rm test
3d6761b8
ngxson
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-08-14
ngxson ngxson merged 77918caf into master 1 day ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone