[ericcurtin]

Description

Changelog title

Probe llmman on port 17434 for manual nodes

Changelog body

• Manual nodes running llmman are now detected as Ollama-API engines.

Bumps

• services: minor
• nvpair-cluster-manager: none
• nvpair-engine-manager: none
• nvpair-errors: none
• nvpair-job-scheduler: none
• nvpair-manual-nodes: minor
• nvpair-node-info: none
• nvpair-node-scanner: none
• nvpair-node-settings: none
• nvpair-proxy: none
• nvpair-tui: none
• nvpair-ui-broker: none
• nvpair-workload-manager: none

llmman is a local model runner that serves the Ollama API on port 17434. Manual nodes were probed for Ollama on 11434 only, so a device running llmman was reported as having no inference engine even though ollama-proxy can route to it unchanged.

• manager.go: probeOllamaAPI tries 11434 then 17434 and reports the answering port in ollama_port; Ollama wins when both answer. 11434 literals become an ollamaPort constant.
• No broker/proxy/desktop changes: ollama_port is already forwarded to ollama-proxy, which already dials it. llmman is not added as a new engine type, per CONTRIBUTING.
• manager_test.go: TestProbeOllamaAPIFallsBackToLLMMan covers Ollama-wins, llmman-only and neither.
• README documents the probe order.

Scope

In: probing llmman on its default port, docs, test, version bump. Out: llmman as a managed local engine, mDNS-discovered nodes, non-default ports.

Validation

Testing: gofmt -l ., go vet ./..., go test ./... -count=1 in services/nvpair-manual-nodes and services/nvpair-ui-broker - clean (macOS arm64, Go 1.26). Not run against a live llmman/Ollama through the full broker/proxy path.

Risk

IPC shapes unchanged; ollama_port may now be 17434. One extra plain-HTTP probe per node per cycle when 11434 does not answer.

Checklist

• I have read the Contributing Guidelines.
• Every commit is signed off (git commit -s), certifying the Developer Certificate of Origin.
• New or existing tests cover the change.
• Relevant documentation is updated.
• I checked the diff, changed filenames, and commit messages for credentials, private data, internal URLs, internal issue identifiers, and generated artifacts.
• I recorded the validation commands and results above.
• I declared version bumps in the release-intent block above. services/versions.json is written by automation, not edited by hand.

AI-assisted, reviewed before submitting.

[Noah-Tervalon-Nvidia]

Thanks for opening this up and for your interest in PAIR! We're going to look into this and decide whether or not we want to bring this in.

[ericcurtin]

Thanks for opening this up and for your interest in PAIR! We're going to look into this and decide whether or not we want to bring this in.

@Noah-Tervalon-Nvidia cool, any feedback let me know

[ericcurtin]

Rebased onto develop.

[ericcurtin]

@Noah-Tervalon-Nvidia @ckelseynv Rebased and added the release intent block, PTAL. Thank you!

[ericcurtin]

@nv-pgoode @kjlubick PTAL when you get a chance. Thank you!

[kjlubick]

We are currently trying to get some other big changes in for the next release so most external PRs are on pause for a few days.

[ericcurtin]

Thanks for the update, no rush.

[ericcurtin]

Thanks for the update. If useful, please try https://github.com/llmmanorg/llmman when you get a chance.

[ericcurtin]

@Noah-Tervalon-Nvidia @kjlubick Gentle ping, PTAL when you get a chance. Thank you!

[ericcurtin]

Merged develop and made the new test table-driven with testify (af74c6d). @nv-pgoode @ckelseynv PTAL when you get a chance. Thank you!

[ericcurtin]

@Noah-Tervalon-Nvidia @kjlubick PTAL when you get a chance. There are no conflicts and tests pass. Thank you!

[Noah-Tervalon-Nvidia]

@Noah-Tervalon-Nvidia @kjlubick PTAL when you get a chance. There are no conflicts and tests pass. Thank you!

Hi, sorry, I've been out on vacation - the code looks fine. Before we add checks for llmman, can you give us some info about usage of llmman? How many people actively use this? One of the things we're worried about is bringing in something that has a smaller user base and then having to manage maintaining it in our code base.

[ericcurtin]

Thanks Noah. llmman started in March 2026 and has 575 stars and 69 forks. Its release assets have about 73k downloads, but that includes CI and repeat installs, and I have no telemetry on active users. The change is a small fallback probe and I am happy to maintain it. Please close it if the user base is too small for now.

[Noah-Tervalon-Nvidia]

Thanks for the info, we're going to focus on larger backends for now, but we really appreciate your interest in PAIR!