From 4607604ef7662ba6dfbfaddf11f3d3fcccfbed39 Mon Sep 17 00:00:00 2001 From: Frank Date: Sat, 17 Oct 2026 21:02:16 -0700 Subject: [PATCH] docs(frank-zealot): carry the 19:44 production boot into the runbook Left uncommitted by the deploy session: the production decode rate (75.8 t/s, within 1% of the trial arm), the shipped boot ledger, the live probe census, and the picker-row law (OpenWebUI meta.description is live DB state a swap must follow into the database, written without restarting open-webui). --- .../LLM/frank-zealot-llama-prism-bonsai2-pq20.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md b/serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md index 1a9dd29..d2ee43c 100644 --- a/serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md +++ b/serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md @@ -103,6 +103,10 @@ DSpark drafter boot in the llama.cpp eras. Any resize must re-read the settled |Two concurrent streams, 256 tok each|**54.7 + 54.7 = 109.4 t/s aggregate** — `--parallel 2` really batches| |Long-context retrieval (25,960-token prompt, needle at position 180 of 300 passages)|exact: *"Frank keeps the fleet in git, only through it."*| +Production boot (the 19:44 cutover deploy, same binary/flags/file): **75.8 t/s** +single-stream decode at a short prompt — within 1 % of the trial arm, so the +ladder above carries to the shipped shape. + ## Behavior contract (probes, not assumptions) - **Reasoning** lands in `reasoning_content` (`--reasoning-format deepseek`) ✓. @@ -165,6 +169,18 @@ DSpark drafter boot in the llama.cpp eras. Any resize must re-read the settled (`/home/dank/models/Qwen35-9B-HauhauCS-Q6K/`, `~/GitPackages/llama-master/build-cuda/`), and the retired era keeps its own page: [[frank-zealot-llama-qwen35-9b-q6k-2x200704]]. +- **Deployed 2026-10-17 19:44** (`deploy.sh dankclaw --service frank-zealot + --service homepage`): boot ledger 22,664 used / 1,461 free, engine fit + projected 21,439 and left 2,119 ≥ 1,872 MiB, KV 13,328.00 MiB at + `n_ctx_seq = 200,704`, `n_slots = 2`, projector loaded; live probes green + (`/v1/models` serves `frank-zealot`, exact `pong` + `reasoning_content`, + `tool_calls` `{"city":"Seattle"}`, 512 px PNG → **Red**). e2e gate 33/33. +- **Picker row is live state:** the OpenWebUI `model` row's + `meta.description` named the 9B, so it was re-keyed in the database too + (backup `webui.db.bak-20261017a`). The row was written WITHOUT restarting + `open-webui` — the cached list refreshes on its next restart, and forcing one + would have logged every family session out for a cosmetic string. See + [[OpenWebUI]] for the picker trio. ## Related