For nc state hpc infrastructure and platform teams

NC State HPC: typed GPU request or scavenger restart?

Connect the first useful exception with the relevant runtime evidence. Did the submission include the GPU type required by NC State?

Replay one resolved incident Try 30 days free

Free 30-day Team evaluation. No card or automatic subscription. Work email verification required.

Why this workflow may fit NC State HPC

NC State documents typed GPU requests under Slurm and separate short or scavenger access to partner GPUs. Its quick start notes the LSF transition.

Read the official NC State HPC workflow reference NC State HPC additional implementation context

Evaluation scope: Preserve the current Slurm versus legacy LSF boundary. Scavenger interruption is a capacity policy, not proof that the job checkpoint is complete or the device is damaged. Use approved redacted evidence. No native integration, automatic repair or current outage is implied.

Prepared from public materials. This is a proposed evaluation, not a report of an incident at NC State HPC or an endorsement.

Selectable demo logs are shared examples, not logs from NC State HPC. Upload a shareable incident from your own workflow to evaluate the fit.

Live diagnosis, no signup

Replay a resolved NC State HPC workflow incident

Upload your log file. Review the selected evidence and masking, then run diagnosis. Keep the original log for any follow-up questions.

Before uploading, review cloud data handling and local options.

training_logs.txt

No log to hand? Try one:

Upload or drop a plain-text log

Upload your log file. Large files are processed in your browser. Only selected evidence is submitted when you run diagnosis.

3 free diagnoses/day

Try Denpex for 30 days. FREE.

No credit card. No automatic subscription. See whether Denpex helps with an incident you already understand.

Start your free 30-day Team evaluation

Up to 50 diagnoses a day for 30 days. Verify your work email to activate an eligible company evaluation, then replay a resolved incident and compare the evidence and next steps with your team's confirmed cause.

What a useful evaluation should establish

Compare one incident your team already resolved with the first failure, cited evidence and remaining questions. Did the submission include the GPU type required by NC State? Only assign a rank, device or safe recovery state when the submitted evidence establishes it.

Did the submission include the GPU type required by NC State?

Evidence to compare: Requested partition, typed GRES selection and scheduler rejection or allocation result.

An untyped request can be rejected before model code starts. Check the documented resource grammar rather than treating this outcome as a failed CUDA initialization.

Was the job pending or had application execution begun?

Evidence to compare: Scheduler reason, allocation start time and the first application output.

A queued request has not necessarily run model code. Separate resource eligibility and scheduling from a process that starts successfully and later crashes.

Was termination expected under the selected capacity policy?

Evidence to compare: Scheduler termination reason, allocation end time and last completed save.

A preemptible allocation can end without an application defect. Match the termination reason and inspect persisted state before diagnosing a device fault or suggesting resume.

Use Denpex alongside your existing telemetry tools to investigate submitted incident evidence. With monitoring configured on a supported plan, detected failures can trigger alerts and an automatic diagnosis from the captured evidence.

Inside Denpex

See the evidence, not just the claim

Follow the causal chain, inspect the quoted evidence and prepare the next handoff. These actual product captures use founder-account examples and the VS Code extension, with the source identified under each image. Open a capture to inspect it at full size.