docs(fv-ml1): add curated LLM seat catalog (lineage/provenance/cards/speed) + bench script

Adds docs/pfi/llm-seat-catalog.md, the durable hand-curated record of what each
seat IS -- lineage, provenance, model-card facts, quantization, speculative
decoding, licenses, and measured warm tok/s + deep-prefill depth results with
their harness and date. It complements the auto-generated
fv-ml1-gpu-seat-inventory.md (live placement/KV/concurrency): the two split by
volatility, and the catalog defers to the inventory for any live number.

Adds scripts/seat-bench.py so the catalog's speed/depth numbers are reproducible
(warm decode tok/s, n=3, conc=1, median; deep prefill at ~0.97x max-model-len
with an allocator-log OOM scan). Serial by design -- concurrent deep prefills
would confound both OOM and tok/s.

Captures the 2026-09-14 measurements: all six generative seats prefill to ~255K
(coder ~16K) with zero OOM/CUBLAS/illegal-memory; warm decode 62.7-337.3 tok/s;
per-seat VRAM. seat-inventory.py now cross-links the catalog in its footer.

docs/pfi/fv-ml1-gpu-seat-inventory.md

@@ -6,7 +6,7 @@
      Hand-edits are overwritten and, worse, drift silently while looking
      authoritative — which is exactly the failure this file replaced. -->
 
-**Generated 2026-09-14 17:24 UTC** by `scripts/seat-inventory.py`, read from the running
+**Generated 2026-09-14 17:45 UTC** by `scripts/seat-inventory.py`, read from the running
 containers on `100.64.0.7` — `docker inspect`, `nvidia-smi`, each model's own
 `config.json`, and the `.PROVENANCE.txt` siblings on `/tank`.
 
@@ -18,11 +18,11 @@ containers on `100.64.0.7` — `docker inspect`, `nvidia-smi`, each model's own
 | GPU | seat | VRAM | weights | KV tokens | ctx | concurrency | util |
 |---|---|---|---|---|---|---|---|
 | 0 | `vllm-cyberprev` | 46.0 GiB | 25.11 GiB | 359,372 | 262144 | **1.37×** | 0.40 |
-| 0 | `vllm-gen-small` | 35.3 GiB | 23.98 GiB | 670,142 | 262144 | **2.56×** | 0.48 |
-| 1 | `vllm-meromero-rp` | 41.3 GiB | 19.51 GiB | 320,774 | 262144 | **1.22×** | 0.52 |
-| 1 | `vllm-erp-seat` | 26.4 GiB | 15.9 GiB | 534,649 | 262144 | **2.04×** | 0.24 |
+| 0 | `vllm-gen-small` | 35.8 GiB | 23.98 GiB | 670,142 | 262144 | **2.56×** | 0.48 |
+| 1 | `vllm-meromero-rp` | 43.0 GiB | 19.51 GiB | 320,774 | 262144 | **1.22×** | 0.52 |
+| 1 | `vllm-erp-seat` | 27.1 GiB | 15.9 GiB | 534,649 | 262144 | **2.04×** | 0.24 |
 | 1 | `vllm-reward` | 9.0 GiB | 4.41 GiB | 26,224 | 16384 | **1.60×** | 0.10 |
-| 1 | `vllm-coder` | 5.5 GiB | 2.98 GiB | 77,056 | 16384 | **4.70×** | 0.055 |
+| 1 | `vllm-coder` | 6.1 GiB | 2.98 GiB | 77,056 | 16384 | **4.70×** | 0.055 |
 | 1 | `vllm-embed` | 3.4 GiB | 1.12 GiB | 10,272 | 8192 | **1.25×** | 0.03 |
 | 1 | `vllm-rerank-a3` | 2.1 GiB | 1.06 GiB | — | 8192 | — | 0.03 |
 | 2 | `vllm-flash-next` | 93.1 GiB | 76.82 GiB | 344,155 | 262144 | **1.31×** | 0.96 |
@@ -133,6 +133,8 @@ context.
 
 ---
 
+*Lineage, provenance, model cards, measured tok/s and depth results live in the hand-curated companion [`llm-seat-catalog.md`](llm-seat-catalog.md).*
+
 *Regenerate with `scripts/seat-inventory.py` after ANY seat change —
 model swap, quant change, context or utilization edit, or speculative-decoding
 change. Run `--check` in CI to catch a stale document.*

docs/pfi/llm-seat-catalog.md

@@ -0,0 +1,159 @@
+# LLM seat catalog — fv-ml1
+
+The durable, curated record of **what each LLM seat IS**: lineage, provenance,
+model-card facts, quantization, speculative decoding, and measured speed/depth.
+
+**This file is hand-curated and complements the generated inventory.** The two split
+by volatility:
+
+| file | owns | updated by |
+|---|---|---|
+| [`fv-ml1-gpu-seat-inventory.md`](fv-ml1-gpu-seat-inventory.md) | **live** placement, VRAM, KV tokens, concurrency, quant format, gateway aliases | `scripts/seat-inventory.py` (read-only, auto) |
+| **this file** | **durable** lineage, provenance, cards, licenses, measured tok/s + depth results, "why this seat" | **by hand**, on seat change or re-bench |
+
+Where they overlap (ctx, concurrency, VRAM), the **inventory is authoritative for the
+live number**; the values here are point-in-time and dated. If they disagree, the
+inventory won and this file is stale — fix it.
+
+## Keeping this current
+
+Update this file whenever a seat changes — model swap, quant change, context/KV edit,
+or a new seat. Two commands regenerate the inputs:
+
+```bash
+scripts/seat-inventory.py            # live placement/KV/concurrency (docs/pfi/fv-ml1-gpu-seat-inventory.md)
+scripts/seat-bench.py                # warm tok/s + deep-prefill OOM check (serial; prints the numbers below)
+```
+
+⚠ **Speed and depth numbers are measurements, not facts about the weights** — they
+carry a date and a harness. Re-run `seat-bench.py` after any context/KV/quant/spec
+change and update the table with the new date. A number without its harness is not a
+result (see the measurement-discipline note at the bottom).
+
+---
+
+## Summary (measured 2026-09-14, harness below)
+
+| seat | GPU | model | ctx | conc. | warm tok/s | VRAM | depth verified | OOM |
+|---|---|---|---|---|---|---|---|---|
+| **cyberprev** (sec) | 0 | Qwen3.8-27B cyber-SFT (abliterated base) | 262,144 | 1.37× | 136.6 | 47.1 GiB | 259,722 tok | none |
+| **gen-small** | 0 | Qwen3.6-35B-A3B Heretic | 262,144 | 2.56× | 254.8 | 36.1 GiB | 254,526 tok | none |
+| **gen** (flash-next) | 2 | Qwen3.8-Flash-Next (orcarouter) | 262,144 | 1.31× | 170.7 | 95.3 GiB | 254,273 tok | none |
+| **char-rp** | 1 | G4-MeroMero-v2-31B (Gemma4 dense) | 262,144 | 1.22× | 62.7 | 42.3 GiB | 254,858 tok | none |
+| **char-rp-fast** | 1 | G4-MeroMero-26B-A4B (Gemma4 MoE) | 262,144 | 2.04× | 225.2 | 27.0 GiB | 254,823 tok | none |
+| **coder** | 1 | Qwen2.5-Coder-1.5B (base) | 16,384 | 4.70× | 337.3 | 5.6 GiB | 15,905 tok | none |
+
+Support (non-generative): **reward** Skywork-Reward-V2-Llama-3.1-8B (9.2 GiB, GPU1),
+**embed** Qwen3-Embedding-0.6B (3.4 GiB, GPU1), **rerank** bge-reranker-v2-m3
+(2.1 GiB, GPU1). **gen (flash-next) is on GPU2 and off-limits to rearrangement;
+GPU3 is reserved scratch (empty).**
+
+---
+
+## Seats
+
+### cyberprev — the `sec` / `sec-reasoning` seat (GPU 0, :8025)
+
+- **Serves gateway:** `sec`, `sec-reasoning`. Displaced mog-sec 2026-09-14.
+- **Lineage:** `Qwen/Qwen3.8-27B` → `hotdogs/Qwen3.8-27B-abliterated` (abliterated base)
+  → **offensive-security tool-calling LoRA** trained on `hotdogs/cyber-sft-agent-qwen38`
+  (8,400 rows, 22 pentest tools: nmap/sqlmap/metasploit/hydra/…), merged @ scale 1.0
+  = `hotdogs/Qwen3.8-27B-abliterated-cyber-preview` → **in-house name-repair** (the raw
+  export shipped 850/1199 body tensors with a tripled `language_model.` prefix — an
+  unsloth export bug, see [[reference_unsloth_tripled_prefix_export_bug]]) → **house
+  mixed NVFP4 quant** → `/tank/aimodels/cyberprev-nvfp4-mixed-v2`.
+- **It is a cyber SFT finetune**, NOT "an abliteration" — the abliteration is inherited
+  from the base; the new capability is the cyber tool-calling SFT. Card: tool-call
+  format 0/6→6/6, correct tool 0/6→6/6, general capability held (KL 0.04 general /
+  0.81 tool = surgical re-target). "Will not refuse" per its card.
+- **Quant:** compressed-tensors mixed — NVFP4 W4A4 on MLP layers 0-55, FP8 W8A8 on
+  attn/linear_attn/lm_head/MLP 56-63, FP8 KV. 15 MTP tensors grafted (bf16), vision
+  tower + `re:^mtp.*` in ignore. Pipeline: `services/gen-seat-mixed-quant/`.
+- **Speculative:** dflash k=7 (drafter `qwen38-27b-dflash2-drafter`), ~2.77 mean accept len.
+- **Context:** native 262,144, **depth-probed clean to 259,722 tokens** (non-repeating
+  prompt). Notable: same base arch as the retired mog-sec, which crashed above ~163,840
+  on processing depth — cyberprev does not.
+- **License:** apache-2.0.
+
+### gen-small — the fast A3B tier (GPU 0, :8026)
+
+- **Serves gateway:** `gen-small`, `gen-small-reasoning`, and backs `summarizer` +
+  `classifier` (the bulk/triage aliases). Stood up 2026-09-14.
+- **Model:** `llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-NVFP4-Experts-Only`
+  → `/tank/aimodels/qwen36-35b-a3b-heretic-nvfp4`.
+- **Lineage:** `Qwen/Qwen3.6-35B-A3B` (3B-active MoE, 256 experts, hybrid GDN+attn) →
+  **Heretic v1.3.0** abliteration (MPOA — Magnitude-Preserving Orthogonal Ablation, the
+  house-favorite method) → NVFP4 experts-only quant. **3.8 was requested but there is no
+  general Qwen3.8 A3B** (the 3.8 MoEs are Flash-Next and the 2.4T), so this is the 3.6
+  fallback.
+- **Card:** 88% fewer refusals (10/100 vs 83/100 original) at 0.0015 KL divergence
+  (quality preserved). 19 MTP tensors preserved (native).
+- **Quant:** modelopt NVFP4, experts-only (256 experts NVFP4; attn/shared-expert/
+  linear_attn bf16). Serves as-is, no re-quant.
+- **Speculative:** qwen3_5_mtp k=3, **measured 69.6% acceptance / 3.09 mean length** — MTP
+  is a clear win here.
+- **Context:** native 262,144, depth-clean to 254,526. Cheap KV (A3B + fp8) → 2.56×
+  concurrency on only 8 GiB KV.
+- **License:** apache-2.0 (per base `Qwen/Qwen3.6-35B-A3B`).
+- **Why:** high-volume, low-caliber work (summarization, classification, triage) belongs
+  on a fast 3B-active seat, not the premium gen seat.
+
+### gen — flash-next (GPU 2, :8022) — off-limits to rearrangement
+
+- **Serves gateway:** `gen`, `gen-large`, `gen-reasoning`, `summarizer-large`,
+  `classifier-large`, `image-judge`, `chat-judge`, `qwen-image-bench`.
+- **Model:** `orcarouter/Qwen3.8-Flash-Next-Uncensored-NVFP4` → **in-house PLE bf16→FP8
+  conversion + `layer_types` rename** → `/tank/aimodels/qwen38-flash-next-orcarouter-nvfp4-plefp8`.
+  See [[reference_qwen4exp_ple_loader_branch_order]].
+- **Lineage:** `Qwen/Qwen3.8-Flash-Next` (176B total: 125B main + 51B n-gram PLE table,
+  ~6B active) → orcarouter uncensored NVFP4 → in-house PLE→FP8 so vLLM's
+  `Qwen4ExpPLEEmbeddingMethod` selects the FP8 path.
+- **Architecture:** the only seat whose weights don't fit its card — the 51B PLE table
+  lives in **pinned host RAM**, read over CUDA UVA. GDN linear-attn + QSA hybrid.
+- **Quant:** compressed-tensors mixed (W8A16 attn / W4A16 experts) + FP8 PLE.
+- **Speculative:** MTP k=3, ~60.4% acceptance.
+- **Context:** 262,144, depth-clean to 254,273. Fastest prefill of the fleet (27.7s/254K).
+
+### char-rp — the char quality tier (GPU 1, :8016)
+
+- **Serves gateway:** `char-rp`, `char-rp-reasoning`.
+- **Model:** `/tank/aimodels/meromero-v2-nvfp4-work/G4-MeroMero-v2-31B-NVFP4A16` —
+  in-house build, **Gemma4 dense, 60 layers**, heretic-abliterated, compressed-tensors
+  NVFP4 W4A16.
+- **Speed:** 62.7 tok/s warm — the slowest seat, inherent to a dense 31B; this is the
+  **quality** tier. Deep prefill 267s/254K (slowest). Gemma4 sliding-window attn
+  (window 1024) keeps KV cheap at depth.
+- **Context:** 262,144 @ 1.22×, depth-clean to 254,858.
+
+### char-rp-fast — the char speed tier (GPU 1, :8021)
+
+- **Serves gateway:** `char-rp-fast`.
+- **Model:** `/tank/aimodels/G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16` —
+  in-house build, **Gemma4 MoE (26B-A4B)**, heretic-abliterated, compressed-tensors
+  NVFP4A16.
+- **Speed:** 225.2 tok/s warm — the throughput answer to char-rp's quality. 2.04×
+  concurrency (KV pinned ~8.5 GiB). Depth-clean to 254,823.
+- **Context:** 262,144 @ 2.04×.
+
+### coder — FIM code-completion (GPU 1, :8020)
+
+- **Serves gateway:** `coder-fast`. Backs Zed edit-predictions.
+- **Model:** `Qwen/Qwen2.5-Coder-1.5B` (base, unquantized), fp8 KV.
+- **Speed:** 337.3 tok/s (smallest model, fastest). Context 16,384 @ 4.70×.
+- **Note:** util-sized; the ~4.7× overshoots the "2-3×" intent because the 1.5B
+  weight+overhead floor (~4.2 GiB) sits just under the util knob's resolution. Hitting
+  ≤3× reliably needs a `--kv-cache-memory` byte pin (compose change), deferred.
+
+---
+
+## Benchmark harness (state it with any number above)
+
+- **warm decode tok/s:** greedy (temperature 0), **conc=1** (single stream), **n=3**
+  reps, median, fixed ~40-word prompt → 300 output tokens. Decode throughput —
+  generation is never prefix-cached, so reps are valid; spread was <1% on every seat.
+- **deep prefill / OOM:** one **non-repeating** random prompt at ~0.97× max-model-len,
+  8 output tokens. PASS = returns AND the seat's allocator log shows **no OOM / CUBLAS /
+  illegal-memory** across the probe window (verified 2026-09-14, 0 hits on all seats).
+- **Measured serially** (one seat at a time) — no cross-seat contention. These are clean,
+  uncontended, single-stream **ceilings**; real aggregate throughput under concurrency is
+  higher per-GPU and lower per-request. Re-derive with `scripts/seat-bench.py`.