dev-1.0.x -> main #116

Merged
alpha-nerd merged 5 commits from dev-1.0.x into main 2026-06-16 11:33:09 +02:00

5 commits

Author SHA1 Message Date
cef71df3df
feat: add ctx-size for llama-swap models to dashboard
All checks were successful
PR Tests / test (pull_request) Successful in 1m19s
NYX Security Scan / nyx-scan (pull_request) Successful in 6m15s
2026-06-15 19:09:55 +02:00
aa8baebac5
feat: add llama-swap as a backend
All checks were successful
PR Tests / test (pull_request) Successful in 1m18s
NYX Security Scan / nyx-scan (pull_request) Successful in 6m19s
2026-06-14 16:34:31 +02:00
c8da58430a
fix: logic extend on total_load AND loaded_count 2026-06-13 15:54:46 +02:00
5184123fd2
fix: improve routing logic to favour unloaded backends instead of looking at per-model load now looking at backend total load 2026-06-13 10:22:20 +02:00
b28f175b61
feat: transparent openai responses api integration 2026-06-10 18:48:26 +02:00