llama.cpp
Server: when no slot is available, defer the task instead of returning "slot unavailable"
#5018
Merged

Server: when no slot is available, defer the task instead of returning "slot unavailable" #5018

ngxson
server: defer task when no slot is available
bf0daf49
remove unnecessary log
558cd1d6
lemmi
ngxson
ggerganov
ggerganov approved these changes on 2024-01-18
ggerganov ggerganov merged 821f0a27 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone