For profluent infrastructure and model engineering teams
ProGen3 job failed: GPU compatibility, input or distributed scoring?
Compare the protein-model launch with the first worker error. Separate an unsupported environment from input parsing or an incomplete output artifact.
Free 30-day Team evaluation. No card or automatic subscription. Work email verification required.
Replay a resolved Profluent 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.
Upload your log file. Large files are processed in your browser. Only selected evidence is submitted when you run diagnosis.
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 has already resolved with the first failure, quoted evidence and remaining questions. Begin with this question: Does the runtime meet the GPU requirements of this release? Only assign a process, device or recovery state when the submitted evidence establishes it.
Does the runtime meet the GPU requirements of this release?
Evidence to compare: Actual GPU architecture, precision setting and attention-extension traceback.
The repository describes tested hardware and kernel constraints. An environment mismatch needs different investigation from an allocation failure during scoring.
Did scoring fail on the input contract?
Evidence to compare: Redacted FASTA structure, sequence-length validation and the first parser exception.
Establish that input preparation completed before attributing failure to FSDP. Use an approved structural example rather than proprietary protein sequences.
Did every expected output finish writing?
Evidence to compare: Per-rank completion status, output inventory and the failing process timeline.
A partial results file can survive a failed distributed job. Confirm completion before presenting an incomplete score set as a successful run.
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.
Follow the failure through the cascade
Prepare the hardware escalation
Ask for the evidence that is missing
Keep the investigation in the editor
