Point Maven at the workstation model: a workstation block, and routing plus replies through llm.Pair #97

Merged
kami merged 5 commits from task/485-run-the-big-model-on-the-workstation-wit into master 2026-08-03 10:13:10 +02:00

5 Commits

Author SHA1 Message Date
claude 4fae13af75 docs: record the workstation routing numbers where the router is documented (V-485)
CLAUDE.md carried only the homesrv figures, which now read as the whole story.
Also points offload.md's order at #490 for the naming half.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1
2026-08-03 10:12:21 +02:00
claude 774217199e docs: measure gemma-4-12b on the workstation against the resident model (V-485)
Both fixtures, run from homesrv across the LAN with the proxy env stripped.
Routing: 84.4% full / 93.5% intent-only at p50 329ms through the cascade, against
72.7% / 77.9% at p50 0.80-1.04s for Qwen3-1.7B. Talk: 25/27 against 20/27, with
knowledge 9/9. Nudges 15/15. Settles #485's first assumption by measurement.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1
2026-08-03 10:12:21 +02:00
claude 2db59d52a7 deploy, docs: point homesrv at bugmachine and say what is still unwired (V-485) 2026-08-03 10:12:21 +02:00
claude 92d5fd580c mavend: route and reply through the workstation when its card is free (V-485)
modelSeam builds an llm.Pair when a workstation is configured and hands it to
the router and the replier. Both are the silent half of the degradation rule:
the big model is only better there, and he is never told which model answered.
No block, no probe, and the box behaves exactly as it did.
2026-08-03 10:12:21 +02:00
claude edeef19ff0 config: a workstation block, dropped when it names no address (V-485)
Health defaults to the supervisor's /health rather than llama-server's,
because mavgpud is what answers 503 while the card is held.
2026-08-03 10:12:21 +02:00