llama.cpp
server: (router) move model downloading to dedicated process
#24834

Merged

server: (router) move model downloading to dedicated process #24834

ngxson merged 13 commits into ggml-org:master from ngxson:xsn/server_download_dedicated_process

server: real-time model load progress tracking via /models/sse

177707e1

update docs

aecc4b32

server: move model download to child process

e86a1843

ngxson changed the title ~~Xsn/server download dedicated process~~ server: (router) move model downloading to dedicated process 10 days ago

github-actions added examples

github-actions added server

Merge branch 'master' into xsn/server_download_dedicated_process

cb14e1c5

rm unused

97b817b3

fix most problems

5134ad01

clean up

938aef1e

nit fixes

26944efe

ngxson marked this pull request as ready for review 9 days ago

ngxson requested a review 9 days ago

ServeurpersoCom approved these changes on 2026-06-21

Merge branch 'master' into xsn/server_download_dedicated_process

5ca1c8e5

fix test case

6c361fb8

github-actions added python

do not detact() thread

8accf886

shorter MODEL_DOWNLOAD_TIMEOUT in test

38d62318

throttle

66b3bc60

ngxson merged 721354fb into master 8 days ago

Reviewers

ServeurpersoCom

Assignees

No one assigned

Labels

examples python server

Milestone

No milestone