serverAppConfigs/serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai9-mtp.md

type, title, description, tags, timestamp

type	title	description	tags	timestamp
reference	frank-zealot on Dankclaw — llama.cpp (PrismML fork 10777), Bonsai-2-9B PQ2_0 with the MTP head, 2 × 262144, exact f16 KV (ACTIVE)	The ACTIVE frank-zealot runbook (since 2026-10-18) — the PrismML fork build 10777 of llama.cpp serving prism-ml/Ternary-Bonsai-2-9B-gguf at PQ2_0 on the RTX 3090: TWO conversations of 262,144 tokens (every slot at the model's trained window) over an UNQUANTIZED f16 K + V cache, vision through the publisher's Q8_0 Qwen3-VL projector, and the boot-arm census that put speculative decoding OFF by measurement even though the checkpoint carries the MTP head.	llm frank-zealot dankclaw llama-cpp gguf rtx3090 mtp spec-decode	2026-10-18

frank-zealot — llama.cpp (PrismML) Bonsai-2-9B PQ2_0 + MTP head, 2 × 262,144, exact f16 KV

Live since 2026-10-18, replacing the frank-zealot-llama-prism-bonsai2-pq20 era (Ternary-Bonsai-2-27B PQ2_0 at 2 × 200,704). The original trade: the 9B bills half the KV per token of the 27B, and that is what funded three conversations at the model's native 262,144 window where the 27B afforded only two shortened ones (Frank's ask: "if you can possibly fit a third context, do it").

The shape moved again the same evening (Frank: "shift frank-zealot to 2 parallels of unquantized kv"). The KV cache went exact — f16 K + f16 V, no quantization error anywhere in the attention state — and the slot count paid for it: 3 → 2. The per-slot contract never moved; every conversation is still 262,144, still the trained window. What the dtype bought is fidelity, and what it costs is one concurrent conversation plus the bytes attention reads per generated token.

Payload identity

Item	Value
Runtime	/home/dank/GitPackages/llama-prism-b10777/llama-server — PrismML fork build, --version → 0.2.0-dev (build 10777, commit e3de71522)
Checkpoint	/home/dank/models/Bonsai2-9B-MTP/Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf — 2,675,410,720 B, Hub-LFS sha256 c79fcdfaf6b7bf47089b50dadcfd11f9ce7d3e96adf3bbefde7912e5ef69e22b
Vision	/home/dank/models/Bonsai2-9B-MTP/Ternary-Bonsai-2-9B-mmproj-Q8_0.gguf — 624,229,664 B, Hub-LFS sha256 e0cb6f6988cea323ef798cd77d019bbb819af75582f034eaab0e7232314953db
Fetch	scripts/download-frank-zealot-bonsai9.sh [DEST] (--verify-only; -f, byte-count and LFS sha256 per file)
Alias	frank-zealot (ALIAS); the SERVICE/unit/scripts keep the StarCraft name, only the wire id is the model id
Port	7771, root systemd unit frank-zealot.service (relinked), TimeoutStopSec=180

The runtime lock has two tumblers now

1. The tensor type. general.file_type 141 with 202 tensors of the fork's PQ2_0 type (of 442 total; the rest are f32 norms/scalars and 8 q8_0 in the MTP block) plus prism.hadamard.* metadata (normalized-sylvester-walsh-hadamard, block_size 4096, axis input-last-dimension, sign_mode explicit over 201 weight names, inverse on token_embd.weight, gdn_v_grouped true). Stock llama.cpp refuses the custom type at load; a loader that ignored the Hadamard metadata would dequant wrong, silently. Same lock class as the ROCmFPX era.
2. The build floor. The fork's card gates MTP beside a quantized V cache on prism-b10776-d00e252 or newer, which is why the prebuilt moved 10754 → 10777 for the swap. Exact f16 KV makes that gate moot — there is no quantized V to pair with the drafter — but tumbler 1 pins the runtime on its own: stock llama.cpp cannot load this file at any flag value. The 10754 tree stays on disk (~/GitPackages/llama-prism/) as the 27B rollback runtime. tests/frank_zealot_unit.bats pins both paths.

Header census (read from the GGUF, not the card)

general.architecture qwen35, general.name Ternary-Bonsai-2-9B, general.size_label 9B, general.quantization_version 2, general.file_type 141:

Key	Value	Note
qwen35.block_count	33	32 trunk blocks + blk.32 = the MTP block
qwen35.full_attention_interval	4	⇒ 8 full-attention + 24 Gated DeltaNet trunk layers
qwen35.context_length	262,144	native; the deployed slot equals it
qwen35.embedding_length / feed_forward_length	4,096 / 12,288
attention.head_count / head_count_kv	16 / 4
attention.key_length / value_length	256 / 256
ssm.conv_kernel / state_size / group_count	4 / 128 / 16	the 27B: 4 / 128 / 16
ssm.time_step_rank / inner_size	32 / 4,096	the 27B: 48 / 6,144
rope.freq_base / dimension_count / dimension_sections	1e7 / 64 / [11,11,10,0]
qwen35.nextn_predict_layers	1	the MTP head is IN the file
general.sampling.*	temp 1.0 / top_p 0.95 / top_k 20 / min_p 0.0 / repeat 1.0	the card recipe; llama.cpp reads it itself

KV accounting. Only the 8 full-attention layers scale with context: 8 × 4 KV heads × 256 dim = 8,192 elements/token per cache (the engine prints n_embd_k_gqa = n_embd_v_gqa = 1024). The deployed pair is exact: f16 K + f16 V bills 32,768 B/token (2 B/element × 8,192 elements × 2 caches), so the 524,288-position pool is 16,384 MiB. The q8_0 pair this endpoint shipped first billed 17,408 B/token — 1.0625 B/element, 32 codes plus one 2-byte scale per 32-block — the 13,056.00 MiB its ledger printed at the 786,432 pool, exactly HALF the 27B's 34,816 B/token.

Corrected arithmetic, and it matters. The note that lived here and in frank-zealot.env — "f16 would bill 26,112 MiB" — doubled the q8_0 figure including its scale overhead, overstating exact KV by 6.25 %. Exact f16 at the 786,432 pool is 24,576 MiB against the 24,123 MiB the driver leaves addressable (nvidia-smi's total column reads 24,576; used + free reads 24,123 — the difference is driver reservation). The wall stands in both readings; the honest rate is what makes the fit calculable instead of superstitious. Halving the POOL is what funds exact KV — the window is already at the native ceiling and there is no YaRN in this path.

The 24 DeltaNet layers bill a fixed recurrent state per SLOT instead: the 3-slot ledger printed RS buffer size = 150.75 MiB (3 cells, 32 layers, 3 seqs) ≈ 50.25 MiB a cell, so two slots bill 100.50. The SPEC-ARMED arms printed 452.25 MiB — MTP depth 2 bills three seqs per slot, so the drafter triples even the recurrent state. Pool arithmetic alone under-prices the shape.

The shape (scripts/frank-zealot.env)

--ctx-size 524288 --parallel 2 (⇒ n_ctx_slot = 262,144), --flash-attn on, --cache-type-k f16 --cache-type-v f16, --batch-size 4096, --ubatch-size 2048, --n-gpu-layers 99, --jinja, --reasoning auto, --reasoning-format deepseek, --metrics, --mmproj …, --log-verbosity 4, --presence-penalty 1.0, SPEC_TYPE=none (which strips --spec-type AND every --spec-draft-*).

Per-slot window is the contract the harness quotes: models.yml carries contextWindow: 262144, and it did not move with the slot count because llama.cpp divides --ctx-size across slots. It refuses a prompt longer than the SLOT with a 400 naming the limit — never a truncation — and since this swap the slot window equals the native window, so no YaRN and no cap is in play. tests/frank_zealot_unit.bats now gates the arithmetic: the shipped dtype × pool plus the measured non-KV ledger terms must fit 24,123 MiB with ≥1 GiB of slack, and the gate is proven to REFUSE the impossible arm (exact KV at the old 786,432 pool = 24,576 MiB of cache alone).

The MTP verdict: the head is in the file and it is still OFF

The drafter is good: acceptance 0.798 / 0.617 per position, mean accepted length 2.41, and the card recommends depth 2. It is OFF because the draft context bills its own f16 KV over the WHOLE pool — blk.32 carries real attention (4 KV heads × 256 × 2 caches × 2 B = 4,096 B/position at the default dtype). The draft dtype is itself a knob — --spec-draft-type-k / --spec-draft-type-v, both default f16, verified against this build's --help (so the "no flag exists" claim that lived here is FALSE) — and quantizing the draft to q8_0 would bill 2,176 B/position, 1,088 MiB at the shipped pool. No measured arm runs a drafter beside exact KV; every row below is f16 draft.

The census below is the q8_0 era: every row is q8_0 K + q8_0 V at the 786,432 pool, where the draft bill was 3,072.00 MiB and 4,830 MiB with its compute buffers. Booted arms, same card, same traffic, 2026-10-18 (/completion timings, greedy 512 tokens; never the first request after a boot):

slots	spec	ubatch	used / free	decode	3-stream	prefill @106k
3 × 262,144	off	2048	17,876 / 6,249	167.2	280.2	2,877
3 × 262,144	on	2048	22,706 / 1,419	109.2	—	—
3 × 262,144	on	1024	21,400 / 2,725	213.5	250.8	2,395
2 × 262,144	on	2048	17,178 / 6,947	213.2	—	—
1 × 262,144	on	2048	11,652 / 12,473	214.2	—	—

MTP is worth +28 % single-stream decode whenever the card has room (rows 4–5 prove the drafter itself is a win; row 2 proves the squeeze is what halves it). The arm that ran it at three windows was SPEC_TYPE=draft-mtp + UBATCH_SIZE=1024 (row 3), paying prefill −17 % and 2,725 MiB of headroom on a card whose mmproj worst-case lands AFTER the engine's own fit check.

Under exact KV an f16-draft arm is priced out of this card. The draft context is built at the TARGET's pool, so at 524,288 positions it bills 4,096 × 524,288 = 2,048.00 MiB plus its own buffers, on a trunk that already projects ~21,200 MiB of the 24,123 MiB addressable. The doors back to speculation are one window per conversation (row 5's class of shape), KV back to q8_0 with UBATCH_SIZE=1024, or the unmeasured --spec-draft-type-k q8_0 --spec-draft-type-v q8_0 arm — 1,088 MiB of draft, legal on b10777, never booted beside exact KV. Frank chose exact KV over the drafter on 2026-10-18, and the endpoint's actual job is what made that affordable: the fleet's compaction hub is prefill-bound on ~170k inputs, prefill is weight-bandwidth bound and does not re-read the cache per generated token — so the dtype is paid in decode and concurrency, not in the work this service exists to do.

Boot ledger — the q8_0 3-slot production boot (2026-10-18 13:19, under the unit, verbosity 4)

CUDA0 model buffer size  =  2036.71 MiB    # + 257.66 MiB CPU_Mapped (mmap)
CUDA0 KV buffer size     = 13056.00 MiB    # q8_0 K + q8_0 V, 786,432 positions
CUDA0 RS buffer size     =   150.75 MiB    # 3 cells, 32 layers, 3 seqs
CUDA0 compute buffer     =  1409.02 MiB    # + 1088.87 MiB CUDA_Host, 2.84 output
mmproj worst-case (est.) =   868.32 MiB    # 248.10 CUDA + 24.93 CPU, AFTER fit
nvidia-smi settled: 17,922 MiB used / 6,203 MiB free of 24,123
n_slots = 3, n_ctx_slot = 262144, kv_unified = false

No clamp line, no cudaMalloc error. The engine's own projection (21,439-class numbers from the 27B era) excludes the projector — read settled nvidia-smi, never the projection.

The exact-KV boot, measured (2026-10-18 evening, PR #21, under the unit, verbosity 4 — the live shape):

CUDA0 model buffer size  =  2036.71 MiB    # + 257.66 MiB CPU_Mapped (mmap)
CUDA0 KV buffer size     = 16384.00 MiB    # f16 K + f16 V, 524,288 positions
CUDA0 RS buffer size     =   100.50 MiB    # 2 cells, 32 layers, 2 seqs
CUDA0 compute buffer     =  1408.06 MiB    # + 1088.07 MiB CUDA_Host
mmproj worst-case (est.) =   868.32 MiB    # 248.10 CUDA + 24.93 CPU, AFTER fit
nvidia-smi settled: 21,176 MiB used / 2,949 MiB free of 24,123
n_slots = 2, n_ctx_slot = 262144, kv_unified = false

The pre-flight projection was right to the MiB, because the two terms it moved are exact arithmetic: 16,384.00 MiB of KV is precisely 32,768 B/token × 524,288 positions — rate derivation and ledger agree with no slop, which is what buries the old 26,112 MiB figure for good — and the recurrent state is one 50.25 MiB cell lighter (100.50 exactly). Settled card state landed at 21,176 used / 2,949 free, within 24 MiB of the 21,200 / 2,920 projection, DropInPaths empty, no clamp line, no cudaMalloc error. It is a desktop margin, though: the mmproj's 868 MiB worst case is still charged AFTER the engine's own fit check, so ~2 GiB is what an image storm has to live inside.

Measured — the q8_0 3-slot boot (/completion timings, greedy, ignore_eos)

• 168.7 t/s decode — three runs of 512 tokens: 168.4 / 168.7 / 168.7 (the trial arm printed 167.2; same shape, same noise band).
• ~300 t/s aggregate across three concurrent 512-token streams (102.8 t/s per stream, round 1 and 2 both) — the trial arm's 280.2.
• 2,877 t/s prefill at 106,418 tokens — the trial arm; the production boot has not re-run that depth.
• The 27B record it replaces: 76.6 decode, 109.4 aggregate across two streams, 691.7 prefill at 166k. Beaten on every axis.
• The first request after a boot is a warmup artifact (37.7 t/s class) — never report it. And never time a wall-clock aggregate on a generation that stops on its own: a 24-token countdown measured 72 t/s across three streams while the same shape with ignore_eos gave 300.

Measured — the exact-KV boot (floors, not a clean A/B)

Instrument: /v1/chat/completions timings (this fork refuses the raw /completion path for greedy runs — see Contract traps), greedy, ignore_eos, 512 tokens, first request discarded.

Arm	q8_0 3-slot record	f16 2-slot, live co-tenancy
single-stream decode	168.7	134.1 – 141.5 over five back-to-back runs; 145.8 and 163.2 in a lighter minute
concurrent aggregate	≈300 across 3 (102.8 each)	256.6 / 262.4 / 265.1 across 2 (≈128–133 each)
prefill at ~106k	2,877 at 106,418	3,159.5 at 106,282
decode at 106k depth	never measured	71.5

These are floors, not the shape's rates. Someone else was driving the endpoint through the whole window — 56 new prompts on the other slot in three minutes, nvidia-smi at 96 % GPU-util — which is the exact condition the Benchmarking Policy forbids, and a contended deep arm even came back truncated (a 512 KB body accepted as prompt_n = 4). What the floors already support: per-conversation concurrency improved (two streams hold ~130 t/s each where three held 102.8), endpoint aggregate sits ~12 % under the 3-slot record, prefill beat the record (+9.8 %) while contended, and single-stream decode is between parity and −20 % against it. The 1.882× KV byte bill is real; its true size on this card is still unmeasured, and quoting 134 t/s or 163 t/s as "the" number would be a guess in either direction. Re-run the same arms with the box quiet before the figure is carried anywhere else.

Contract traps

• --metrics is mandatory. Without it llama.cpp answers 501 on /metrics, so the Prometheus scrape reads DOWN while /health answers 200 — that is how this endpoint sat red across four payload generations

  (up{job="frank-zealot"} oldest retained sample, 2026-10-11, is already 0).

• Bare /completion is a dead instrument on this fork build. A greedy ignore_eos run answers 500 — "The model produced output that does not match the expected Content-only format", because the fork guards the raw path the moment reasoning markup leaks (older builds only logged failed to parse reasoning content and answered anyway). The honest per-request instrument on THIS build is /v1/chat/completions, whose non-stream response carries the same timings object (prompt_n, prompt_per_second, predicted_n, predicted_per_second). AGENTS.md still names the /completion timings object as this endpoint's instrument — on build 10777 read it off the chat path.

• Q8_0 mmproj, not BF16. The publisher's card: the BF16 tower "can crash llama-server when several image requests run at once; Q8_0 is not affected" — and --parallel 2 is still precisely that shape.

• Only the image_url content part reaches the model. The legacy top-level images field bumps usage.prompt_tokens and the model still invents an answer. Probe with a solid color and expect the exact word.

• ≥256 px probe images or the model answers "video".

• Thinking tokens count against max_tokens. A vision probe at 64 tokens returns EMPTY content + finish_reason: "length" — the endpoint looks blind while it is only mid-thought. Budget ≥512.

• presence_penalty has no GGUF metadata key, so the one recipe value that must reach the argv is this one. The serve script uses ${PRESENCE_PENALTY=1.0} — not := — because "" is the documented opt-out and := would silently re-add the flag (caught by the seam, fixed 2026-10-18).

• Spec flags move as a SET. A bare --model-draft/--spec-type arm without the whole set has segfaulted at load on this fork family in the past; SPEC_TYPE=none strips all of them.

• Base alignment is the censored base lineage, and the CRACK swap is NOT one line here. /home/dank/models/Bonsai2-CRACK/ matches the 27B geometry, not this 9B file; a dealigned 9B would have to be fetched.

• A raw /completion request logs failed to parse reasoning content (… parse_reasoning=true) when the model closes a bare prompt with `` — cosmetic (probe_request.cpp:789); /v1/chat/completions parses reasoning_content correctly. Do not lower VERBOSITY: the KV/buffer ledger is what VRAM forensics read.

• A failed stop leaves a failed unit, and an orphan keeps answering. On 2026-10-18 the trial stop hit State 'stop-sigterm' timed out. Killing. → Active: failed (Result: timeout), while the hand-booted arm kept serving 7771 — a live port with no unit behind it. TimeoutStopSec=180 is now on the unit (llama.cpp needs the drain time to release slots and the card); the hand-booted arm must be killed by PID, never pkill -f llama-server.

• A leftover arm drop-in hijacks the production boot, and no health check sees it. The sanctioned bench method is a transient Environment=FRANK_ZEALOT_ENV_FILE=/tmp/<arm>.env drop-in, and an arm env sources the repo env and then overrides it. On 2026-10-18 a stale frank-zealot.service.d/ptq1.conf — written 03:29 for the 27B PTQ1_0 arm Frank had ordered at 02:36 and measured from 03:14 (deploy ledger below) — was still installed, so the cutover deploy restarted the unit and booted THAT: --model …/Bonsai2-PTQ1_0/Ternary-Bonsai-2-27B-PTQ1_0.gguf --ctx-size 401408 --parallel 3 --batch-size 3072 --ubatch-size 1536, three slots of 133,888, 21,188 MiB used. /health was 200, /v1/models said frank-zealot (the alias is a flag, not a fact), and the Playwright gate passed 33/33 — none of those read the payload. After deploying an endpoint that was recently benched: systemctl show -p DropInPaths, then tr '\0' ' ' </proc/$pid/cmdline, then the ledger — in that order. Retire the drop-in to ~/.AGENTTRASH/<date>-<topic>/, daemon-reload, restart.

Compaction hub

models.yml routes compactionModel for frank-archon, frank-dragoon and frank-zealot here — 262,144 is the widest window in the fleet and the only one that comfortably fits a worst-case compaction input (~170k tokens; the clamp is min(maxTokens 16384, contextWindow − est − 4096), compaction fires at 85 % of the window ≈ 222,822 est, worst case ≈ 245,891 ≤ 262,144). What the reslice to two slots does cost is here: a compaction request still runs beside ONE live generation, but with two conversations already busy a third waits — the Gemma4 era's --parallel 1 serialization law at half strength. The window itself is untouched, and the window is the term the compaction contract depends on.

Deploy ledger (2026-10-18)

• ./scripts/deploy.sh dankclaw --service frank-zealot at 13:16 PDT; the e2e gate ran 33/33. The first boot was the hijacked arm above; the drop-in went to ~/.AGENTTRASH/20261018-zealot-ptq1-arm/ and the 13:19 restart is the ledger recorded here.
• Live probes on the shipped boot: chat 27*59 → 1593; where_am_i tool call fired with schema-correct empty arguments; 512 px solid-red PNG → Red at 278 prompt tokens with process_mtmd chunk encoding in the journal; /props reports n_ctx 262144 and presence_penalty 1.0; /metrics answers 200 with 15 llamacpp:* families and up{job="frank-zealot"} is 1 in Prometheus for the first time in its retained history.
• OpenWebUI picker rows re-keyed in the live DB (Connection.backup() snapshot webui.db.bak-20261018 taken first; frank-dragoon's context.length also corrected 262,144 → 200,704 — see OpenWebUI).
• What the bench window left behind is not garbage — the PTQ1_0 arm was ordered, measured, and then scratched by Frank himself. The instruction at 02:36 was: run frank-zealot on Ternary-Bonsai-2-27B-PTQ1_0.gguf, the Q8 mmproj, batch/ubatch 3072/1536, and as much context as fits in two contexts. The unit booted it at 03:14 (journal: type ptq1_0: 402 tensors, file type = PTQ1_0 - 1.75 bpw ternary, mmproj loaded, 2 × 200,704) and served 24 minutes of traffic. Its own print_timing lines measure ~48 t/s single-stream decode (48.0 / 47.9 / 47.6 / 49.0 t/s on 512 / 229 / 512 / 451-token generations), 25–27 t/s per stream with two streams live, and prefill 1,295 t/s at 30,637 → 943 at 97,856 → 801 t/s at 141,365 tokens. It bought the 1,201 MiB the fetch script promised and paid for it on decode, exactly as the publisher's Ampere row warned (the PQ2_0 record for the same weights is 76.6 t/s). At 03:33 Frank scratched the whole 27B plan and ordered the 9B PQ2_0 + MTP shape deployed here; the arm process ended at 03:38.
• The actual failure was documentation, not measurement. An approved payload that survives only as a systemd drop-in plus a journal window is, a day later, indistinguishable from a rogue arm — which is why the 13:16 boot read as a hijack. Payload decisions belong in this runbook the moment they are made. The evidence is still perishable: /tmp/zealot-arm-current.env and the 9B /tmp/arm-*.jsonl results die on reboot, and only the journal (journalctl -u frank-zealot --since "2026-10-18 03:10") holds the PTQ1_0 numbers. /home/dank/models/Bonsai2-PTQ1_0/ (5,946,648,928 B + hardlinked mmproj) stays on disk as the 27B rollback.

Fallback rungs

Cheapest first; every one is a single line of scripts/frank-zealot.env, and the KV figures are for the 524,288-position pool unless stated otherwise:

1. UBATCH_SIZE=1024 — hands back 1,306 MiB of compute buffers measured on this card (prefill −17 %).
2. CACHE_TYPE_V=q8_0 — exact K, quantized V: the pool goes 16,384 → 12,544 MiB, freeing 3,840, and it is the halfway door back. --flash-attn on is what keeps quantized V legal.
3. CTX_SIZE=401408 — two 200,704 conversations: exact KV at 12,544.00 MiB, same 3,840 freed, but models.yml contextWindow MUST follow the per-slot number or long turns start 400-ing.
4. Revert to q8_0 K + q8_0 V at CTX_SIZE=786432 PARALLEL=3 — the shape this one replaced: 13,056.00 MiB of cache and the THIRD conversation back.
5. CACHE_TYPE_K/V=q4_0 — the far rung: 10,240 B/token ⇒ 5,120 MiB here (the 27B era measured q4_0 at 16,392 used / 7,733 free at 2 × 200,704).

Any retune has to keep the seam's fit gate green — it is the only instrument that can see a boot that would die at cudaMalloc.

Rollback

Revert the swap commit. On disk: the 27B payload (/home/dank/models/Bonsai2-PQ2_0/) + the 10754 fork tree, the Qwen3.5-9B Q6_K payload (/home/dank/models/Qwen35-9B-HauhauCS-Q6K/) + master CUDA build, the Gemma4, MiMo, Swift and Ornith payloads. Then ./scripts/deploy.sh dankclaw --service frank-zealot.

Related

• frank-zealot-llama-prism-bonsai2-pq20 — the retired 27B era (rollback target)
• Llama Cpp Serving Sizing — the two-boot VRAM pricing method
• frank-dragoon-flash-server-v2-native — the other 2026-10-18 cutover
• deployment — deploy flow and incidents