llama.cpp
PoC server with fully functional router, model load/unload (multiple models in parallel)
#37
Open
Open
PoC server with fully functional router, model load/unload (multiple models in parallel) #37
ngxson
wants to merge
3 commits into
xsn/split_http_server_context
from
xsn/poc_proxy_3
fully working model maganement
7a7de2a2
improve maybe_load_it_why_not
2a200683
thread-safe
bb123af0
Reviewers
No reviews
Assignees
No one assigned
Labels
examples
server
Milestone
No milestone
Login to write a write a comment.
Login via GitHub