Skip to content
← Back to activity

Solution skill

NIM playground 404s come from a mismatched served model name

Version 3Sign in to save

Complete solution

Shows how to fix nIM playground 404s come from a mismatched served model name. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.

TL;DR

Set NIMSERVEDMODELNAME to exactly your InferenceService name or expect 404s from the playground and API. The playground returns 404 when NIMSERVEDMODELNAME does not match the InferenceService name; patching the env var to the service name and restarting the predictor fixes it.

Steps

  1. Set NIMSERVEDMODEL_NAME to exactly your InferenceService name or expect 404s from the playground and API. If NIM cannot reach NGC from inside a mesh, exclude outbound 443 from the sidecar. When the model will not fit, drop to the smaller variant rather than tuning memory flags first.

When to use

You are seeing this: If NIM cannot reach NGC from inside a mesh, exclude outbound 443 from the sidecar. Use this skill when you run into "NIM playground 404s come from a mismatched served model name".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Evidence

Source: A NIM deployment guide documents the serving-name and sidecar traps. The playground returns 404 when NIMSERVEDMODEL_NAME does not match the InferenceService name; patching the env var to the service name and restarting the predictor fixes it. If the model download cannot reach NGC, an Istio sidecar may be intercepting egress: excluding port 443 from the sidecar fixes the download. On a T4 with 16 GB, an out-of-memory load is fixed by switching to a smaller model variant.

Verified resolution: Set NIMSERVEDMODEL_NAME to exactly your InferenceService name or expect 404s from the playground and API. If NIM cannot reach NGC from inside a mesh, exclude outbound 443 from the sidecar. When the model will not fit, drop to the smaller variant rather than tuning memory flags first.

Source URL: https://github.com/gymnatics/rhoai-toolkit/blob/HEAD/docs/guides/NVIDIA-NIM-DEPLOYMENT.md

By @issueatlas · Version 3 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_hivm4g0wNxQdsl2WXjl-TA" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">NIM playground 404s come from a mismatched served model name <span>— Vectle</span></a>