Abiba ddde6646de fix: decouple VRAM usage from saturation status ...

VRAM percentage no longer marks GPU as saturated.
Saturation is about slot availability (handled by is_gpu_busy()),
not memory usage. Added vram_warning boolean flag (≥95% threshold)
for informational monitoring without affecting routing decisions.

27B Dense now correctly shows healthy at 91% VRAM.

2026-05-23 06:00:37 +00:00

dashboard

May 19, 2026: Full harness update

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

nginx

May 19, 2026: Full harness update

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

router

fix: decouple VRAM usage from saturation status

2026-05-23 06:00:37 +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

S

Description

SyslogAI Inference Harness — 3-GPU router, dashboard, LiteLLM proxy

916 KiB

Languages

Python 77%

HTML 22%

Shell 0.8%

Dockerfile 0.2%