llama.cpp
server: add strict prompt cache RAM limit
#25070
Merged

server: add strict prompt cache RAM limit #25070

ngxson merged 1 commit into ggml-org:master from tarruda:cache-ram-strict
tarruda
tarruda tarruda requested a review 122 days ago
tarruda tarruda requested a review 122 days ago
github-actions github-actions added server
tarruda tarruda force pushed 121 days ago
tarruda tarruda force pushed 113 days ago
ngxson
tarruda
ngxson
tarruda tarruda force pushed 112 days ago
tarruda
tarruda server: enforce prompt cache RAM limit
13c21c05
tarruda tarruda force pushed to 13c21c05 112 days ago
ggerganov
ggerganov approved these changes on 2026-07-07
pwilkin
pwilkin approved these changes on 2026-07-07
ngxson
ngxson approved these changes on 2026-07-07
ngxson ngxson merged 6c487e2f into master 112 days ago
tarruda tarruda deleted the cache-ram-strict branch 112 days ago
sanmai
sanmai commented on 2026-10-14

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone