server: allow accessing /metrics and /slots during llama_decode() #27041
server_queue::worker
fca17612
call llama_decode inside yield_to_queue
0b42458e
also handle process_mtmd_chunk
a35d2af1
clean up
d809c0f3
nits
98e489eb
ngxson
marked this pull request as ready for review 1 day ago
ngxson
requested a review
1 day ago
ggerganov
approved these changes
on 2026-08-14
rm test
3d6761b8
ngxson
merged
77918caf
into master 1 day ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub