inference-harness

T

Abiba 54a4f26db7 fix: Default tier back to Dense-first (MoE overheating at 91°C)

Heavy tier keeps MoE primary (workhorse for >25K tok).
Default tier routes Dense → VLM → MoE to prevent MoE overload.
MoE had 5 timeouts in 15 min when Default pushed overflow to it.

2026-05-28 21:40:18 +00:00

dashboard

fix: default performance window to 24h so all models appear immediately

2026-05-26 12:37:52 +00:00

nginx

feat: per-request performance tracking + /metrics/performance endpoint

2026-05-25 16:50:45 +00:00

router

fix: Default tier back to Dense-first (MoE overheating at 91°C)

2026-05-28 21:40:18 +00:00

.gitignore

May 19, 2026: Full harness update

2026-05-19 15:03:47 +00:00

docker-compose.yml

fix: non-blocking GPU health checks + 256K turboquant context upgrade

2026-05-23 05:57:13 +00:00

docker-compose.yml.bak

May 19, 2026: Full harness update

2026-05-19 15:03:47 +00:00

litellm_config.yaml

May 19, 2026: Full harness update

2026-05-19 15:03:47 +00:00

maintenance.sh

May 19, 2026: Full harness update

2026-05-19 15:03:47 +00:00