Commit Graph

2 Commits

Author SHA1 Message Date
Hanashi 77524a10e6 final: 5090 tables (incl. bf16-streaming), stats tooling covers all 5 datasets
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-06 19:21:16 -04:00
Hanashi a293d0a2c4 reliability: failure-stats + output-validation tooling; persistent output dir
- bench/failures.py: per-GPU success rates and error-class breakdown by config
- bench/validate_outputs.py: ffprobe every recorded output via /view
- finding: 24GB cards fail on multi-ref (TE vision OOM), not duration/size;
  100% of successful runs produce valid videos
- outputs now written to /workspace (survives pod resets)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-06 14:41:00 -04:00