Journal

A quantization job goes silent

The full-spec job stopped after six of 36 blocks; the monitor detected the dead wrapper and idle GPU.

Vlad / experimentos.
The boundary

Reboot, recorded OOM and contemporaneous GPU faults were excluded. An external kill remains an unconfirmed explanation.

The question

A full-spec quantization job stopped making progress after only six blocks. The incident record follows the monitor, idle GPU and checked failure explanations without inventing a confirmed cause.

From the original notebook

Timeline (NZST, machine clock verified via log correlation)

  1. 12:19 — Full-spec build launched on GPU 0 via ops/hq4-full/retry-wrapper-hq4-full.sh (setsid-detached): 256 samples / seqlen 1024 / 200 iters / grad-accum 8 / symmetric W4A16 G128, target artifacts/MOSS-TTS-v1.5-HQ4-256. Cron monitor MOSSHQ4FULL_HAIKU_MONITOR installed after a passing manual test.
  2. 12:19–12:47 — Healthy progress: 6/36 blocks, steady ~280–295 s/block, per-block loss converging (e.g. 115.2→9.4, 1.66→0.52), peak RAM 45.6 GB, peak VRAM 19.2 GB. Two monitor checks green, Telegram progress updates sent.
  3. 12:47:49 — Last log line (layers.6: 6/36). Process goes silent mid-block-6.
  4. ~14:01 — Scheduled monitor check finds: wrapper dead, quant pid dead, GPU 0 idle, no MONITOR_RESULT, log frozen 73 min. Sends Telegram needs-attention alert (case 4: wrapper died before exhausting retries), keeps cron per its instructions. A second attention check follows.
  5. 14:05 — Human-owned investigation (this entry): rules out reboot (uptime continuous), kernel GPU faults (Xid-free window 12:30–14:05, journal readable), kernel + userspace OOM (no signatures). Remaining explanation: external kill from parallel session activity. Killer unidentified.
  6. 14:0x — Cron entry removed to stop 15-minute alert spam now that a human owns the situation (reversible one-liner, recorded here). No relaunch per explicit user instruction (“don’t quantize nothing else right now”).

Notes

  • An earlier NVRM: Xid 43 at 11:50 is unrelated (predates the 12:19 launch; hit parity/envelope-era processes, which completed normally).
  • work/hq4-full/ contains only backbone_stub/ — nothing to salvage or resume.
  • Open question for the user/peer: did anyone run kill/pkill (or a cleanup matching quantize) between 12:47 and 14:00? Answer would close the case.

Keep exploring

Original experiment record. Workstation paths have been generalized. Detailed measurements below retain their original workload and validation boundaries.

Follow the evidence

From notebook to finding.

This story is based on the archived experiment at revision 6550ead3945b. Original timestamps, workloads and qualification limits belong to that record.

Original GitHub record
Supporting notebooks (2)

GitHub source links require access to the private archive. The readable notes and aggregate chart exports are included here.

Back to the journal Follow via RSS