Grant e88fdcfde4 v0.3.0:1 - hotfix: parallel SSH probes + longer timeout ...

- Hardware probes for spark1 and spark2 now run via asyncio.gather (parallel) so the worst-case wall time is max(per-probe), not sum
- Bump per-probe SSH timeout from 8s to 12s to absorb first-call overhead (StrictHostKeyChecking=accept-new on first connect + nvidia-smi cold start)
- Unreachable Spark now shows up cleanly in the UI as a single 'unreachable' card with the error message

2026-05-12 12:14:36 -05:00

..

app

v0.3.0:1 - hotfix: parallel SSH probes + longer timeout

2026-05-12 12:14:36 -05:00

Dockerfile

Pack spark-control_x86_64.s9pk (55 MB)

2026-05-12 09:52:53 -05:00

entrypoint.sh

Initial scaffold: image/ FastAPI app, models.yaml, docs

2026-05-12 09:29:13 -05:00

models.yaml

Add per-model descriptions + repo-cleanup polish

2026-05-12 10:19:09 -05:00

pyproject.toml

Initial scaffold: image/ FastAPI app, models.yaml, docs

2026-05-12 09:29:13 -05:00