frank-secondary: record the deployed boot, keep the unit description honest

Deploy verified: nvidia-smi 21,436 MiB used / 2,689 free at ubatch 2048 -
the MiMo-priced projection (~21,430/~2,700) landed within 11 MiB, and the
verbosity-4 ledger confirms the KV law to the MiB (CUDA0 KV buffer
12,544.00 MiB = K(f16) 6,272 + V(f16) 6,272 = 32 KiB/token over the
401,408 pool), compute buffers 1,136 MiB CUDA0 + 848 MiB host, mmproj
879 + 248 MiB. Playwright gate: 33 passed.

Two lessons recorded: the 203/EXEC boot loop my shebang-less rewrite
caused (journal signature + the head -1 check), and that llama.cpp's
"n_ctx_seq < n_ctx_train" line is informational when the context is BELOW
the trained window - the Gemma4 drafter warning was the opposite case.

The unit's Description named the Swift-1.5 era (and said 2x131072/q8_0/
draft-mtp); it now names the Q6_K shape. Cosmetic, so it is NOT deployed
as its own restart: the next frank-secondary deploy relinks it.

Co-Authored-By: omp <omp@franksdank.cloud>

AGENTS.md

@@ -451,13 +451,16 @@ decode flat, 616 MiB — MiMo-era A/B on this card), `--log-verbosity 4`,
 property of the file, not of the flags. The publisher card advertises "MTP
 support" for the base architecture; the quantized export dropped the head.
 
-**Measured boots** (nvidia-smi, the referee): the pricing boots are the
+**Measured boots** (nvidia-smi, the referee): the deployed boot is
-MiMo-V2.6-Distill-Qwen-9B pair at this exact geometry — 2 × 200,704 f16 K +
+**21,436 used / 2,689 free** (ubatch 2048) — the pricing boots were the
-f16 V: **21,276 used / 2,849 free** (ubatch 1024) and **21,846 / 2,279**
+MiMo-V2.6-Distill-Qwen-9B pair at this exact geometry (**21,276 / 2,849** at
-(ubatch 2048). This file is 415 MiB lighter in weights ⇒ projected ~21,430 /
+ubatch 1024, **21,846 / 2,279** at 2048), so the 415 MiB lighter weights
-~2,700. The deployed boot ledger: see the runbook. Decode is ubatch-invariant
+bought back what the projection predicted. The engine ledger confirms the KV
-(Swift-era 3090 law). The Q6_K rung costs ~10 % decode vs Q5_K_M (weight
+law to the MiB: `CUDA0 KV buffer size = 12544.00 MiB` (`K (f16): 6272.00`,
-bandwidth; MiMo-measured 94.4 vs 104.8 t/s).
+`V (f16): 6272.00`), compute buffers 1,136 MiB on CUDA0 + 848 MiB host, the
+mmproj 879 MiB + 248 MiB. Decode is ubatch-invariant (Swift-era 3090 law). The
+Q6_K rung costs ~10 % decode vs Q5_K_M (weight bandwidth; MiMo-measured 94.4
+vs 104.8 t/s).
 
 **Vision**: the publisher's own BF16 mmproj via `--mmproj` (the model is
 natively multimodal; the Q6_K file carries no vision tensors). Probe traps

scripts/frank-secondary.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=llama.cpp Swift-1.5-Qwen3.8-27B Uncensored RCO IQ3_XXS GGUF (qwen35 hybrid, 2x131072 slots, q8_0 K+V, draft-mtp depth 3, mmproj vision) on the RTX 3090 (dankclaw, frank-secondary)
+Description=llama.cpp Qwen3.5-9B-Uncensored-HauhauCS-Aggressive Q6_K GGUF (qwen35 hybrid, 2x200704 slots, f16 K+V, MTP off, mmproj vision) on the RTX 3090 (dankclaw, frank-secondary)
 After=network-online.target
 Wants=network-online.target
 

serverAppConfigs-docs/LLM/frank-secondary-llama-qwen35-9b-q6k-2x200704.md

@@ -76,9 +76,30 @@ Ubatch 2048 is the measured CUDA optimum for this card and arch (+4.6 %
 prefill at 8.9k depth, decode flat, cost 616 MiB); `1024` is the documented
 fallback rung if a future shape lands under the 2 GiB floor.
 
-## Measured boot (2026-10-07)
+## Measured boot (2026-10-07, deploy `ec6184d`)
 
-TO BE FILLED BY THE DEPLOY VERIFICATION.
+`nvidia-smi`: **21,436 MiB used / 2,689 MiB free** — the MiMo-priced
+projection (~21,430 / ~2,700) was within 11 MiB. Engine ledger
+(`--log-verbosity 4`, `journalctl -u frank-secondary`):
+
+|Line|Value|
+|---|---|
+|`llama_context`|`n_ctx = 401408`, `n_ctx_seq = 200704`, `kv_unified = false`|
+|`llama_kv_cache`|`CUDA0 KV buffer size = 12544.00 MiB` — `size = 12544.00 MiB (200704 cells, 8 layers, 2/2 seqs), K (f16): 6272.00 MiB, V (f16): 6272.00 MiB`|
+|`sched_reserve`|`CUDA0 compute buffer size = 1136.06 MiB`, `CUDA_Host compute buffer size = 848.07 MiB`|
+|`clip_model_loader` (mmproj)|`model size: 878.99 MiB` + `reserve_compute_meta: CUDA0 248.10 MiB, CPU 24.93 MiB`|
+|`srv load_model`|`n_slots = 2, n_ctx_slot = 200704`|
+|`print_info`|`n_ctx_train = 262144`, `n_head_kv = 4`|
+
+The `32 KiB/token` law is confirmed exactly: 401,408 × 32 KiB = 12,544 MiB,
+which is what the engine printed. The `n_ctx_seq (200704) < n_ctx_train
+(262144)` line is informational (a context **below** the trained window is
+safe; the Gemma4 era's warning was the opposite case, a drafter running 53 %
+**past** its window). Weights load in ~6 s from page cache; `/health` answers
+`{"status":"ok"}` and `/v1/models` serves the alias `frank-secondary`.
+
+The deploy's Playwright gate passed (33 tests) and the fleet e2e set is
+unchanged.
 
 ## Client contract
 
@@ -111,3 +132,11 @@ one slot, not the pool; queue behind two long generations ⇒ the slot ceiling
 is two, by contract; a boot that OOMs ⇒ read the verbosity-4 ledger in
 `journalctl -u frank-secondary` (KV MiB, compute buffers) before touching
 flags — the engine prints the exact figures the shape needs.
+
+**`status=203/EXEC` boot loop**: the rewrite of `serve-frank-secondary.sh`
+shipped without its `#!/usr/bin/env bash` line, and systemd failed the
+`ExecStart` before the script ran — 10 s restarts, `Mem peak: 1.9M`, and
+`nvidia-smi` flat at 1 MiB used (the GPU is never touched). Journal signature:
+`Failed at step EXEC spawning /home/dank/…/serve-frank-secondary.sh`. A
+shebang is not decoration on this host: every LLM serve script is a direct
+`ExecStart`, so `head -1` is part of the deploy check (commit `ec6184d`).