CTX_SIZE 589824 / PARALLEL 3 -> three independent 196,608-token conversations
(a mamba hybrid cannot share one KV cache, so per-slot window = pool/slots;
3 x 262,144 would need 18.4 GiB of KV alone and busts the card).
Vision comes back via bartowski's mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
(918,166,048 B, sha256 ff348f31..., fetched + verified by
scripts/download-frank-small.sh): the Q5_K_M GGUF ships no v.* tensors, so
--mmproj IS the image path. MMPROJ_FILE without a colon default so an explicit
empty value is a real text-only opt-out, and the deployer now gates on the
projector exactly as the serve script does.
Budget is measured, not guessed: the 2 x 262,144 shape used 20,190/24,576 MiB,
which prices non-KV cost at 7,390 MiB. Three slots + projector land near
22.5 GiB, i.e. ~2 GiB spare - the bottom of the requested band, to be
confirmed by measurement and laddered if it lands outside 2-3 GiB.
The repo's highest-quality rung is ftype 115: 311 tensors of
GGML_TYPE_Q8_0_ROCMFPX, a type only the ROCmFPX fork reads, so the runtime
moves from gufo to scripts/build-rocmfpx.sh's pinned fork build (36e9acd) —
the first build on this host measured to load this file without the
2026-08-25 set_rows segfault. One session at the native 262,144 window, f16
KV (64 KiB/token, 16 GiB), the repo's Q4_0 MTP head drafting 4 tokens, plus
the bundled BF16 projector so the endpoint has vision again.
The serve script now honors caller environment overrides over the env file
(a plain source let the file win, which made single-run overrides no-ops) and
defaults apply only when a value is unset, so an explicit LLAMA_BIN='' is the
error it reads as.
One quant step down from Q6_K on the same CUDA build and the same shape:
2 x 262,144 with K f16 + V q8_0. The 0.86 GiB freed from the weights is
headroom, not a new window — the native 262,144 cap is already reached,
and f16 V would still cost 3.96 GiB more than the pool can carry.
The first crash-looping boot (51 restarts): serve received the host path
/home/dank/models/... but the models tree is mounted at /models inside the
container, so transformers failed 'Repo id must be in the form
namespace/repo_name' before the engine even built. Same conversion the spec
draft already used. Pinned by bats. Root docs index links the new runbook
(seam required it) and the work log records the crash-loop plus the 52 G
payload reclaim.
The 2026-10-01 first deploy refused /home/dank/models/Qwen3.5-9B because
the handler checked for a single model.safetensors (the dflash layout);
the Qwen3.5-9B MTP head ships 4 shards behind model.safetensors.index.json.
Same dual-layout acceptance as the serve script, now mirrored and gated by
the seam. The gate fired before the stop, so the live gufo unit was never
touched (health 200 throughout).
Engine: digest-pinned docker.io/kyuz0/vllm-therock-gfx1151 (vLLM 0.30,
TheRock ROCm 10, Triton GDN kernels); the serve script gates the image by
REPO DIGEST, the payload (config + index + exact shard count), the spec
draft (BOTH weight layouts: single model.safetensors for dflash, sharded
index for the Qwen3.5-9B MTP head), and whole /dev/dri, sweeps the bench
identity vllm-mimo, then exec podman wait so a container death trips
Restart=always. Shape: 4 x 262144 at util 0.45 (KV grows only on the 8
full-attention layers), MTP 2 draft tokens.
Measured 2026-10-01 window (frank-large stopped): base 13.1 t/s decode
(~94% of the LPDDR5x BF16 roof), DFlash-8 17.4, MTP-2 19.8 with 71%/44%
per-position acceptance - the cross-model head works because vLLM reads the
draft from a separate path while MiMo ships zero mtp.* tensors. Spec arms
do not preserve greedy bf16 text (batched-verify reduction order).
The seam was rewritten around the new laws (18 tests): unit self-healing,
digest gating, engine wiring, the measured spec table, the retired gufo
gates, the deployer MainPID check. frank_small port test follows the
PORT -> FRANK_LARGE_PUBLISH rename. Rollback: tag frank-large-gufo-q4kxl-20261001.
bf16 at 2 x 262144 fails with and without --expert-precise-memory. The real
error (captured from the journal this time, container fixed via journald
rather than podman logs):
RuntimeError: Worker failed with error 'Constraints violated
(L['query_start_loc'].size()[0])! You marked it as dynamic but your code
specialized it to be a constant (3)'
- a torch.compile/dynamo dynamic-shape violation, NOT an OOM. Ruled out a
stale compile cache: ~/.cache/vllm holds only modelinfos (16K) and each
podman run gets a fresh container filesystem.
The deltas from the last shape measured serving (fp8 3 x 262144 / MNBT 2048 /
792,069 tokens / 3.02x / arena 6,248) are KV dtype (fp8 -> bf16) and SEQS
(3 -> 2). Restoring the known-good shape; bisect bf16 vs SEQS in a window,
with --enforce-eager as the bypass.
NRestarts climbed to 3, each attempt ~6.7 min then 'Deactivated successfully'
(API server drains after an EngineCore fatal error; Restart=always turned the
silent death into a visible loop). The arena is device-resident, so the budget
decides it: weights 6.28 + pool 6.80 (bf16 2 x 262144) + graphs 0.55 + arena
16.65 (precise overhead 5.25) + non-torch 1.45 = 31.73 of 31.86 GiB -> ~0.13
GiB free at boot, and graph capture is what allocates transiently.
Dropping the flag restores the 7.60 GiB default overhead: arena 14.31 GiB,
total ~29.4 GiB, ~2.4 GiB free. bf16 2 x 262144 (Frank's KV change) stays.
The serve script keeps the opt-in flag; the seam now asserts it is ABSENT.
Frank's call. Payload: ajgazin's abliterated Swift-1.5 UD-Q8_K_XL (29.3 GiB,
SWIFT OPEN LICENSE) -> unsloth/Qwen3.8-27B-GGUF UD-Q4_K_XL (16.35 GiB,
sha256 3f227079...b01e, vanilla/Apache-2.0). NOTE: the endpoint is no longer
uncensored — that was one of the reasons for the Swift payload on 2026-09-28.
New fetcher scripts/download-frank-large-q4.sh (no auth header: repo is public
and ungated; size + sha256 verified after transfer). The speculative drafter
and its fetcher are unchanged.
Shape: --sessions 4 --context 163840 with unquantized KV. gufo exposes no KV
quantization lever (execution_policy.hpp pins kv_cache_storage to kFp16), so
f16 is inherent.
KV arithmetic: f16 KV = 64 KiB/token (16 full-attention layers x 4 KV heads x
256 head_dim x 2 x 2B; the other 48 layers are linear-attention with a
per-sequence fp32 state). 4 x 163840 = 655,360 tokens = 40.0 GiB KV, each
session exactly 10 GiB. Budget ~62 GiB of the 114 GiB GTT.
Seam retargeted (FETCH -> the q4 script, TARGET_STUB, context/sessions pins).
Both of Frank's changes at once.
KV is bf16 (--kv-cache-dtype auto) at two full-size windows (2 x 262144).
bf16 measures 13,839 B/token (bf16 3x241664 boot: 11,047,010,304 B -> 798,280
tokens), decomposing as 12,276 attention + 1,563 mamba/side caches vs fp8's
6,138 + 1,563 = 7,701. 524,288 tokens needs 7.256e9 B; pinned at 7.3e9
(~527,500 tokens, 3,206 margin). Pool cost: 5.68 -> 6.76 GiB per rank.
--expert-precise-memory selects the fitted overhead (5.25 GiB) over the default
(7.60 GiB = fitted + compile/graph-capture headroom). It moves only the plan's
term, so the expert arena goes 6,248 -> ~7,278 slots (~1,025 more) at the
cost of boot-time capture slack. Overhead adds 0.22 GiB/1024 nbt above 4096, so
MNBT 2048 pays nothing.
Seam + docs + AGENTS row + log updated.
ExecStop runs 'podman stop -t 120' but the unit never set TimeoutStopSec, so
systemd's 90 s default cut the graceful stop short: journal shows 'Stopping
timed out. Terminating.' then 'Failed with result timeout' on 2026-10-01
13:27:17 — every stop of this unit was logging a failed stop. 180 s covers the
engine's drain with margin, and the seam now guards the RELATIONSHIP
(TimeoutStopSec > the podman grace) rather than a literal.
StartLimitIntervalSec is a [Unit] directive; the copy in [Service] made systemd
log 'Unknown key StartLimitIntervalSec in section Service' on every load. Seam
asserts it appears exactly once and not in [Service].
Frank's call 2026-10-01: MAXLEN 262144 x SEQS 3 = 786,432 tokens of contract.
Measured fp8 KV costs 7,698 B/token (4-slot boot 8,311,013,376 B -> 1,079,582
tokens; 5-slot boot 10,388,766,720 B -> 1,350,182 tokens), so the pool floor
for the contract is 6.054e9 B. Pinned at 6,100,000,000 (~792k tokens, ~5.9k
margin) so the remaining ~2.2 GiB versus the 4-slot shape goes to the expert
ARENA - the fork sizes its decode-critical expert cache from the remainder
after weights, pool and workspace.
MNBT 2048 (Frank): the arena sweep measured 6,499 slots at every rung <= 4096,
so the larger batch costs the arena nothing.
Seam retargeted (3 seqs / 6.1e9 / MNBT 2048); docs + AGENTS row + log updated,
including the closed DCP investigation.
DCP is passed only when FRANK_PRIMARY_DCP is set, so the deployed shape is
unchanged. Verified in this fork: DCP reuses the TP ranks when PCP is
disabled (tp % dcp == 0), so TP=2 + DCP=2 fits the two R9700s with no extra
ranks; the flash_attn backend carries DCP support, the 36 linear-attention
layers of this hybrid do not — which is what the A/B window tests.
Replaces llama.cpp Gemma4-12B-QAT (payload + binary retained as rollback).
SGLang in a self-contained python3.12 venv with an extracted CUDA 13.0
nvcc toolchain for the sgl-kernel/flashinfer JIT.
Shape: fp8 KV, pinned 606,208-token pool / 4 x 151,552 slots, bf16 mamba
states pinned at 32 slots (the engine autofills the ssm pool to a fixed
~5.1 GB regardless of dtype), eager prefill (no headroom for graph
capture), no spec decode (the checkpoint ships no mtp.* tensors despite
mtp_num_hidden_layers=1 — NEXTN drafts with an uninitialised 4.24 GiB
ghost at 0% acceptance).
Verified: 83.9 tok/s decode, 170k single prompt, 4 concurrent 54k
requests, vision (in-checkpoint tower), reasoning_content field.
Five 262144-token contexts passed every boot gate (KV 1,350,182 / 5.15x) but
left 0 bytes free at runtime: a real client request (995-token prompt,
max_tokens=261149, sampling params straight from models.yml) killed Worker_TP1
with torch.OutOfMemoryError 'Tried to allocate 50.00 MiB ... 0 bytes free'.
Boot is not proof of runtime survivability.
Four slots x 262144 fp8 (KV_BYTES 8,311,013,376/rank) returns ~1.93 GiB per
rank for activations/graph capture.
Unit: Restart=always instead of on-failure — a runtime worker fault makes
vLLM's API server exit clean, so ExecStart returned 0 and on-failure never
fired, leaving the endpoint down until a human noticed. Also
StartLimitIntervalSec=0 and OOMScoreAdjust=-500.
Frank's call after the night ladder: five contexts at the model's full native
262,144 window beat six shortened ones. Six full-length contexts do NOT fit at
any KV dtype (6 x 241664 fp8 asked 10.70 GiB against 9.18 GiB free — the
6-seq graph/activation footprint leaves too little for the pool); 5 x 262144
at fp8 PASSED on the first rung: KV_BYTES 10,388,766,720/rank, measured
'GPU KV cache size: 1,350,182 tokens, Maximum concurrency for 262,144 tokens
per request: 5.15x' (39,462 tokens of margin).
Also documented: the SEQS=3 bf16 max (241,664, KV 732,359 / 3.03x) measured
earlier the same night, and the root-cause read that the 7.2 GiB KV ceiling
law was the MTP4 workspace, not VRAM. Seam and harness (contextWindow 262144)
re-pinned.
Night ladder result (Frank's subtract-16k method): 262144 and 245760 both OOM
at CUDA graph capture ('Tried to allocate 76.00 MiB ... 0 bytes free'), 237568
passed (KV 718,606 tokens), and the +4096 bonus step PASSED -> 241664 is max
possible and DEPLOYED at util 0.98 (KV 732,359 tokens / 3.03x concurrency at
241,664-token requests). Util stays 0.98: lowering it shrinks the engine's own
budget instead of buying slack.
Client contract restored (the GLM rollback d91379d dropped all three and the
qwen rollback inherited the gap): --reasoning-parser qwen3 fixes the malformed
thinking block (thinking was landing inline in content with a dangling
</think> and a null reasoning field), --enable-auto-tool-choice with
--tool-call-parser qwen3_xml makes tools work, and
--default-chat-template-kwargs enables enable_thinking + preserve_thinking.
Harness: contextWindow 241664 (compaction gap recomputed), preserve_thinking
moved into chat_template_kwargs.
The 0.98 boot died at KV allocation: torch OOM tried 10.28 GiB (the exact
3x262144 bf16 pool = 11,047,010,304 bytes) with 9.46 GiB free per rank.
The rootless bench probe had booted the same numbers; the root unit's
pinned-expert path holds ~0.8 GiB/rank more. Util 0.90 returns ~2.5 GiB/rank
of workspace with the pool ask unchanged; measured KV capacity law
(798,280 tokens at 11.05e9) unchanged.
Overnight redo campaign verdict + Frank's call: the fp8+MTP4 shape is retired
to git tag frank-primary-fp8-mtp-20261001. The new incumbent: KV cache
unquantized (auto), no speculative decode, KV_BYTES 11,047,010,304/rank
(engine-measured 798,280 tokens, 3.05x concurrency at 262,144-token
requests), MNBT 1024, MoE gather 32x64 (+18.7% decode, grows with depth).
Measured at the deployed shape: 39.38/38.79/36.42 tok/s (166/1087/4064 ctx).
Seam re-pinned: the 7.2 GiB/rank KV ceiling was the MTP4 workspace, not VRAM;
spec decode absent by measurement; bf16 trade documented (clean cache +
262k windows for ~14% decode at 4064 ctx).
- AGENTS.md: fleet table + frank-primary section back to qwen FP8 + MTP4
(37.4-40.6 tok/s, 54% acceptance); GLM runbook moved to the retired index.
- runbook: RETIRED verdict — DFlash2 drafter served and drafted but
acceptance pinned 1.00-1.38 on every text class including verbatim
repetition (mis-wired aux capture, not a weak drafter); 5x slower than
baseline at ~1.2 acceptance.
- log.md: 2026-10-01 rollback entry.
- deploy-remote.sh: LLM_PRIMARY_CONTAINER back to frank-primary-qwen;
glm-probe joins the legacy sweep list.
- frank_primary_unit.bats: re-pinned to the qwen shape — KV qualification
law (7.2 GiB/rank, 3.65x concurrency; 9/16 GiB OOM), fp8 q8/q8 KV
PRESENT, MTP4 PRESENT (3.1-3.4x over the 12.11 no-spec baseline), no tool
dialect, automatic offload. The old 'MTP buys zero' law carried the
prefetch tax and is retired.
The deployed unit failed its first boot with the engine core OOMing during
profile/graph capture: "Tried to allocate 662.00 MiB. GPU 0 has a total
capacity of 31.86 GiB of which 240.00 MiB is free ... try setting
PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True". The expert-offload plan
fills VRAM to its modelled headroom by design, so the default allocator's
fragmentation leaves the capture phase nothing — every successful bring-up
probe (both scratch-port and 7770) carried this env, and the repo recipe
dropped it.
Also pins the seam: the setting is part of the qualified shape, not an
optional tuning.
Payload: Intel/GLM-5.3-Flash-W4A16-AutoRound (AutoRound symmetric int4 group
128, auto_round:auto_gptq, 34 shards + 2 extras, 113,074 tensors, ~170 GiB).
It is the only W4A16 checkpoint this fork can serve with expert offload: its
quant_method "auto-round" is overridden to "inc", which routes the MoE to
libr4d's grouped W4A16 GEMM (R4dW4a16MoEMethod). A compressed-tensors W4A16
build of the same model resolves to TritonWNA16Experts, which has no offload
recipe, and refuses to serve at all (170 GiB of experts cannot fit 64 GiB of
VRAM, so offload is mandatory).
Shape: tcclaviger RDNA4 vLLM fork (same digest-pinned image as the 2026-09-29
qwen cutover), TP=2, 131,072 ctx x 2 seqs, bf16 KV (fp8 is ILLEGAL here — it
disables the sparse MLA backend's rope-free Triton path, the only MLA decode
gfx12 has), util 0.98, NBATCH 2048, --enable-expert-offload
--expert-precise-memory, prefix caching, glm47 tool + reasoning parsers,
MTP and expert prefetch absent by measurement.
Measured: decode 9.9-10.0 tok/s, prefill 918 tok/s (warm), arena 14.51 GiB =
2,383 slots/rank over 12,096 host-backed experts (73.64 GiB pinned/rank).
THE 35 tok/s TARGET IS NOT MET and the shortfall is measured: live telemetry
(R4D_LRU_TELEMETRY=1) gives a 0.53-0.66 per-layer hit rate, a step moves
0.82 GiB of misses in ~100 ms = 8.2 GB/s effective against a link measured at
22.74 GB/s — the same structural gather-path gap the qwen campaign found.
Growing the arena 13.08 -> 14.51 GiB changed decode by nothing.
Rejected by measurement: MTP4 (head loads, acceptance 3.76-4.90, but decode
unchanged and prefill collapses 918 -> 255 — a verification forward gathers the
union of the batch's experts), NBATCH 8192 (identical prefill).
Also: scripts/patches/gpu_worker-kv-cap.patch (fork-local fix for a KV-reserve
model that under-counts GLM's per-sequence KDA state; not needed by this shape),
runbook, AGENTS.md row + section, both indexes, work log.
Rollback: 2339fae (qwen FP8 + MTP4).
Replace the R9V radiance fork with the tcclaviger RDNA4 vLLM stack (the
digest-pinned image the 2026-09-29 tuning campaign measured), serving
orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8 (131 shards, 172.8 GiB,
already on disk) with MTP4 spec decode.
Qualified by boot probe on 2026-09-29:
- MAXLEN=200000 x SEQS=3 (600k total) at --kv-cache-dtype fp8 (q8/q8 KV):
'GPU KV cache size: 729,545 tokens; Maximum concurrency for 200,000
tokens per request: 3.65x' at KV_BYTES 7.2 GiB PER RANK.
- KV_BYTES is per-rank: global 16G and 9G both OOM (worker tried to
allocate the full size; ~7.5 GiB/rank is the ceiling with the arena).
- prefetch OFF by law (telemetry: 36% precision, ~50% wasted traffic);
TunableOp off (corrupts numerics).
- decode at this shape: 42.94/34.55/36.09 tok/s; arena 6,032 slots.
Trio: frank-primary.env (all FRANK_PRIMARY_* keys), serve-frank-primary.sh
(direct podman run; entrypoint execs vllm serve; waits on the container),
frank-primary.service (root unit, same ExecStop law, new container name
frank-primary-qwen). Deployer gates rewritten (image digest + shard count
+ weight-map index). download-frank-primary.sh is now inventory/verify
(repo is GATED — 401 anonymous, masked LFS hashes; payload already on
disk). Seam rewritten for the new contract. Pre-cutover tag:
frank-primary-r9v-q8-20260929.
The ad-hoc status commands kept producing wrong readings, most seriously
reporting "MemAvailable 0.0 GiB" on a host that actually had 240 GiB free.
Cause: /proc/meminfo separates key from value with a TAB, so
grep MemAvailable /proc/meminfo | tr -s " " | cut -d" " -f2
returns an empty field and awk prints 0.0. A false "host is out of memory"
reading is worse than no reading, because it invites an unnecessary abort.
dankstatus.sh parses on a colon split (tab-agnostic), cross-checks
MemAvailable against MemTotal before printing either, and refuses to print
a zero value. It also pins the rocm-smi CSV column order (device, total,
used) which was previously read swapped, and takes only the first line of
systemctl is-active/is-enabled, which emit more than one line here.
Incidental finding while validating: rocm-smi reports card2 (the 7700X iGPU)
as 0.50 GiB total, not the 123.0 GiB torch.cuda reports. torch was exposing
the GTT aperture. The device is smaller than documented, not larger.
Tests: 346/346 pass (no test surface touched).
The .AGENTTRASH archive is ignored and exists only in a primary checkout,
so a filesystem grep fails there while passing in a worktree. git grep
searches the tracked tree, which is what the assertion is about.
gufo is a vertical inference engine built for exactly this hardware
(Ryzen AI MAX+ 395 / Radeon 8060S, gfx1151), and Dankclaw's frank-large
has swapped runtimes seven times in search of a better one. This one
ships no prebuilt Linux binary, so the runtime is BUILT FROM SOURCE on
the host and the payload, port, alias and client contract stay exactly
where they are.
Runtime: gufo v0.1.1 (b0f8673) at /home/dank/GitPackages/gufo-v0.1.1,
built by the new scripts/build-gufo.sh. It links the host ROCm 7.2.4
through its RPATH — the opposite of the unsloth prebuilt it replaces,
which carried its own — so two host workarounds are encoded in that
script: Ubuntu's librocwmma-dev installs a truncated rocWMMA header set
that shadows AMD's and cannot be overridden with -I in HIP mode, and the
ROCm clang prefers Ubuntu 26.04's GCC 16 headers over the GCC 15 whose
libstdc++ is actually installed.
Shape is unchanged: one session, full 262144 ctx, the same UD-Q8_K_XL
target and the same DFlash2 drafter, greedy, text-only. Speculation
moves from llama.cpp's fixed depth 4 to gufo's adaptive block policy
capped at 7 proposals.
Client-contract deltas, all documented: the chat template is compiled
into the binary (no --chat-template-file, so the Qwen-Sharp 73k-token
failure mode is gone), reasoning_effort now takes the full OpenAI set
(so models.yml's reasoningEffortMap fold is no longer required — kept
anyway, so this commit does not also move every high role from xhigh to
high effort), and there is no KV-quant or prompt-cache-RAM flag.
The test seam now runs the serve script against a stub engine and
asserts on the argv it actually execs, instead of grepping the script's
text. The deploy handler gates on the runtime binary and returns before
it stops the serving unit.
Measured trade, from gufo's own Q8_K_XL tables against llama.cpp
b11069: prefill +37% to +80%, cold load 4.5x faster, decode +7% at zero
depth — but -14% at 65,536 tokens of depth and -24% at 131,072. On the
8-bit target the crossover is ~32k, and frank-large runs one 262,144
conversation. The Q4_K_XL target shows no such regression.
Replace the vLLM 0.30 UVA-offload wiring (never deployed; llama.cpp
b11030 endpoint replaced by Frank's order, downtime window open) with
the R9V radiance-vLLM shape on the same root unit:
- serve-frank-primary.sh: layer the on-host qualified setup state
(104 tuned R9V_* keys, /home/dank/r9v-state/uncensored/setup.json)
under repo production overrides, then exec the fork's own launcher
through the docker->podman shim and block on docker wait so a crashed
engine is a nonzero ExecStart (launch.sh --detach alone would fake
green). Gates: pinned image by OCI manifest digest in RepoDigests,
PLE at pinned byte count (stat -c %s), all GGUF shards + mmproj.
- frank-primary.env: thin production overrides only (LAN bind 0.0.0.0,
:7770, alias frank-primary, container frank-primary-r9v, GPU BDFs);
tuned engine shape stays in the setup state by design.
- frank-primary.service: same root-unit shape (User=dank,
LimitMEMLOCK=infinity for the tiered-expert pin), plus ExecStop
podman stop — docker wait cannot stop the container child.
- deploy-remote.sh deploy_llm_primary: state-driven gates (state ready,
image digest present in rootless storage, PLE bytes, shard files)
replace the fp030 shard-index gate; false-green MainPID check kept.
- tests/frank_primary_unit.bats: seam rewritten for the R9V shape.
The llama.cpp b11030 trio becomes the vLLM 0.30 trio ahead of the
FP8 cutover on :7770 — same port, same alias, no client moves.
Serve shape: locally built ROCm gfx1201 image
(localhost/frank-primary:vllm030) execs via podman as dank from the
root unit (LimitMEMLOCK=infinity legalizes the pin). UVA offload:
--offload-backend uva pins the PLE family (47.75 GiB, 138 tensors:
131 n-gram table shards + 7 per-layer conv/proj) + routed experts
(114.86 GiB, 150,528 tensors) in host RAM — 162.60 GiB combined,
~81.3 GiB per rank under TP=2, hence --cpu-offload-gb 82 (80/card
strands 2.6 GiB of experts on the cards). Parsers per the host's
own Ornith-era precedent: qwen3_xml tools + qwen3 reasoning (vLLM
0.30 emits the channel as `reasoning` — reasoning_content is
renamed server-side) + enable_thinking/preserve_thinking template
kwargs. Spec decode stays env-wired and OFF at bring-up.
Deployer deploy_llm_primary rewritten: image gate, index-driven
shard-count gate (131), stale-container cleanup, port wait, and the
false-green hardening — health is only green when the unit's own
MainPID is live behind the answer (2026-09-26 lesson).
Seam tests rewritten to the vLLM contract (15 gates): offload
arithmetic, parser wiring, no-llama.cpp-ism, deployer gates. Suite
349/349 green.
The stock SearXNG image ships a native kagi engine; enabling it needs an
API key that must never enter git, and SearXNG does not expand env vars
in settings.yml (the live secret_key literally was '${SEARXNG_SECRET}'
until now — the app tolerated the placeholder string silently).
- settings.yml: kagi engine enabled (weight 2, kg shortcut, paging off so
exactly one API credit per aggregated query, timeout 8.0 vs 5.0 scrapers
so a slow paid query is not a wasted credit); api_key stays ${KAGI_API_KEY}.
- new scripts/searxng-render-settings.py: deploy-time renderer, allowlisted
to KAGI_API_KEY/SEARXNG_SECRET/SEARXNG_BASE_URL, fails the deploy loudly
on an unresolvable placeholder, idempotent on redeploys.
- deploy-remote.sh copy_searxng_config runs the renderer against
/opt/searxng/.env after copying settings.yml into /opt/searxng/config.
- KAGI_API_KEY placeholder added to dankclaw/.env.example (real key staged
into the host-side /opt/searxng/.env, mode 600, out of band).
- bats: engine wiring, renderer substitution, loud-failure, deployer seam.
- docs: SearXNG.md Kagi section + renderer law; Providers.md carve-out on
the no-credentials policy (paid engine acceptable when bounded + ordered).
Verified live on dankclaw: direct API probe via the gluetun netns (200,
data.search[] shape), then an aggregated query returned 29/29 results
tagged kagi, zero unresponsive engines.
Blocks 0-4 on ROCm0 + 45-47 on ROCm1. This exact shape was probed and
battery-verified earlier the same session: card0 2.54 GiB free at boot,
2.11 GiB after the vision graph (steady under load), card1 unchanged
at ~3.3 GiB. Card1 cannot take another block (0.82 GiB would OOM the
vision graph + boot drift), so 5/3 is the physical limit at the
4x262144 / V-q8_0 shape. OT assertion pins the new value.
- CONTEXT_SIZE=1048576 / PARALLEL_SLOTS=4: four conversations, each the
full native 262144 window (per-slot window unchanged; slots divide
the pool, they never multiply it).
- CACHE_TYPE_V=q8_0 / CACHE_TYPE_K=f16: main KV drops 24,576 -> 18,816
B/token (-23.4%); the shared MTP drafter's KV ignores the V type
(measured: 2,048 MiB draft pool = the f16 law at 1,048,576 cells).
- OT_OVERRIDES: blocks 0-3 on ROCm0 and 45-47 on ROCm1 stay
GPU-resident (2.42/2.49 GiB per block, measured); the rest stay
CPU-computed. Measured free under load: ~4.9 GB card0 / ~3.4 GB
card1; a 5th block on card0 lands at 2.27 GB, under the 3 GB
checkpoint floor, so blocks are atomic and 4 is the safe fill.
- serve script: --cache-type-k/v env-wired tunables; ONE joined
--override-tensor flag (b11030 deprecates repeated flags, and the
loader is first-match-wins, so the specific patterns must precede
the broad exps=CPU sweep).
- seams: the window test asserts per-slot = 262144 at 4 slots; new
KV-type test; OT exact-value assertion pins the ordering law.
Discovery, not guesswork: dump the GGUF v3 headers of the fetched parts
(scripts/dump-gguf.py, added — a dependency-free reader that never
touches tensor data, so a 50 GiB part scans in milliseconds) before
the first load.
What the dump says (parts 2-3, 2026-09-26):
- The 51B-param PLE n-gram table is ONE tensor: per_layer_token_embd.
weight, dims [160, 320001536], Q8_0, 54.4 GiB — exactly the whole of
part 3. It is the same tensor the shared MTP head borrows, so the
=CPU override is required for placement AND for the draft load
(GPU-resident borrow: "invalid vector subscript").
- The model is qwen4exp, 512 experts, top-10 routing
(qwen4exp.ple.ngram_size=3, heads_per_ngram=8).
- Part 1 is metadata-only (ntensors=0); parts 2-6 carry tensors.
The placeholder pattern ngram_embeddings matched nothing — dropped from
OT_OVERRIDES (env, serve-script default, seam, AGENTS.md, runbook,
LLM index) before it could masquerade as a working override at load
time. Deployed set: exps=CPU,per_layer_token_embd.weight=CPU.
Suite: 346 green.
The 2026-09-26 same-day cutover that ended the Lucebox DS4.1 detour:
Dankserver's :7770 endpoint is now unsloth llama.cpp (the b11030-mix
prebuilt, ROCm gfx120X, bundled runtime) serving
unsloth/Qwen3.8-Flash-Next-GGUF at Q8_0 — 175.30 GiB across six sha256-
verified split parts — on both Radeon AI PRO R9700s, as a ROOT unit (the
frank-large shape: no container, no generated unit).
The deployed contract:
- Placement law: layer split -ts 1,1 with -ngl 999; the routed experts
and the 51B-param n-gram (PLE) table are COMPUTED in host RAM via
-ot exps=CPU,ngram_embeddings=CPU (the x4-pair measurement: streaming
over PCIe loses at 3.7 t/s, computing in RAM does not care).
per_layer_token_embd.weight=CPU is required by the shared MTP head's
borrow path (a GPU-resident borrow crashes the draft load).
mmap stays on; --cache-ram 16384.
- Spec chain draft-mtp,ngram-mod: the shared Q8_0 MTP head
(mtp-...-shared-Q8_0.gguf, 2,786,568,256 B) at depth 2, with the
draftless ngram-mod matcher chained behind it — the only legal way to
layer two spec implementations in one process.
- Vision explicit: --mmproj names the BF16 projector (this build never
autoloads; a server without it comes up healthy and text-only).
- Reasoning: --reasoning-format deepseek → reasoning_content; the
Qwen3.8 template's {xhigh, medium, low} reasoning_effort gate folded
by reasoningEffortMap in models.yml.
- One stream, the model's full 262,144 context; greedy server default
with Qwen-recommended sampling riding compat.extraBody.
The deployer's deploy_llm_primary is rewritten for the root unit: it
gates every artifact at its declared byte count (stat -c %s, never wc -c
— which read the whole 377 GiB lucebox file for minutes on 2026-09-26),
retires the lucebox user quadlet to dated home trash, waits out port
7770, relinks/enables/restarts the root unit and waits up to 1800 s for
/health. The quadlet-era tree under dankserver/frank-primary/ is
archived (dankserver/.AGENTTRASH/20260926-llamacpp-cutover/ on this
box; git history everywhere else) and its planner mapping replaced by
the scripts/ trio.
Observability flips back to the llamacpp namespace: a frank-primary
Prometheus job at 192.168.0.235:7770 (cross-host LAN — the netavark
published-port quirk that forces host.containers.internal for the two
Dankclaw endpoints is same-host only), the LlmEndpointDown runbook
text, and the dashboard description for three llama.cpp endpoints.
Docs: the new runbook (frank-primary-llamacpp-qwen38-flash-next-q8.md),
RETIRED banners on the lucebox and radiance runbooks and their index
entries, the AGENTS.md fleet section rewritten for the root-unit shape,
and the homepage frank-medium card renamed to frank-primary with the
Q8_0 Flash-Next spec (docs.html #models and the modality note updated:
images on frank-primary and frank-small, audio on frank-small only).
models.yml: the dankserver provider is "llamacpp (dankserver)" serving
frank-primary, contextWindow 262144, maxTokens 65536 (compaction-gap
law: 183,501 + 65,536 <= 262,144), input [text, image].
Suite: 346 green (frank_primary_unit.bats rewritten for the root unit —
16 tests pinning the placement law, the shared-head requirement, the
explicit projector, HIP env hygiene (BIND_HOST, never bare HOST), and
the deployer's byte-count gates; the quadlet-era planner and
changed-tests mappings rewritten for the trio; the observability scrape
test asserts three llamacpp jobs again).
Rollback: the lucebox image (localhost/lucebox-rocm:gfx1201) and the
378 GiB payload stay on the host; the Qwen payload stays fetched, so a
re-swap in either direction is a redeploy, not a refetch.
The frank-medium retirement tail the 2026-09-26 lucebox cutover left
uncommitted: the radiance quadlet tree, its swap/fetch tooling and its
seam test are deleted (archive copies live in dankserver/.AGENTTRASH/
20260926-frank-medium-radiance/ and scripts/.AGENTTRASH/20260926-
frank-medium-radiance/), the planner/allowlist/test-changed mappings
drop the service, and frank-large's chat template moves to scripts/
(its old home was the retired frank-medium dir).
Finished here:
- tests/frank_primary_unit.bats: the lucebox quadlet seam (boot
persistence, host-network bind, HIP_VISIBLE_DEVICES=0,1, HIP-reserved
env-name guard, checkout-mounted entrypoint/healthcheck, first-start
patience, deployer payload/port gates).
- test-changed.sh: explicit .AGENTTRASH/ case — retirement commits move
files to trash, and the wrapper refused those additions with "no
focused-test mapping".
- observability: the vllm: namespace left with the radiance runtime.
Rules keep only llamacpp:* series (prefix-cache reuse, spec-decode,
queueing, endpoint-down); the dashboard drops the vLLM KV/latency
panels; prometheus.yml documents that frank-primary (lucebox) has no
/metrics and therefore no scrape job. llm-fleet.json was left
corrupted mid-edit (missing opening brace) and is rewritten from HEAD.
Suite: 339 green (was 7 red).
Replaces frank-medium (vllm-radiance TP=2) on :7770. The 377.2 GiB
43-layer MoE (256 routed experts, top-6) is mmapped: dense work and the
MLA KV cache on the R9700, routed experts computed on CPU from the
page cache (246 GiB RAM). The unit bypasses the image entrypoint
(Qwen/DFlash-only flag set) and execs luce_server with the DS4 launch
shape; --ds4-fused-decode's monolithic-load fallback IS the serving
mode here. deploy_llm_primary gates on image + model byte count,
stops/masks the radiance unit, waits for :7770, installs and starts.
Runbook: frank-primary-lucebox-ds4.md.
systemd splits unquoted Environment= values on whitespace, so the
quadlet quotes OAUTH_SCOPES to keep all four scopes; update the bats
assertion to expect the quoted form (it was checking the old
unquoted line and failing).
fill-verify-Enter with a single inputValue read per stage (identification
and password); the toHaveValue assertion hard-failed every attempt when the
re-render wipe landed inside its 5s window (00-auth.setup failure 2026-09-24)
The qwen_image21 detection check and GGUF node arch list patch are
applied by a startup wrapper (comfyui-start.sh) that runs before
ComfyUI starts. The patch script and wrapper are baked into the image
so they survive container recreations. The quadlet's Exec now points
at the wrapper instead of main.py directly.
Swap the serving checkpoint back to
just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (quark/W4A8) and serve it with
KV_DTYPE=auto (unquantized bf16 KV) instead of the hardcoded fp8. fp8 KV
stacked on MXFP4's already-quantized W4A8 weights compounds attention-path
precision loss; clean KV tests whether that was hurting output quality. The
freed MXFP4 weights (19.37 vs 30.9 GB) buy the KV pool back, so the full
262,144 native window fits unquantized - MAXLEN returns to 262144.
The entrypoint gains a KV_DTYPE tunable (default fp8, the historical behavior),
shared across both quantization paths; the quadlet sets auto. Rollback: SNAP
back to the FP8 checkpoint with KV_DTYPE=fp8 and MAXLEN=192000.
The user page now orders Web Apps, Media Library Apps, AI — the models sit
at the bottom, below the apps people click. The AI card and /docs#models
descriptions drop the infrastructure (runtimes, GPUs, tensor parallelism,
draft heads) in favor of what users care about: the hosted model, its
size, the context/parallel capacity, and what it's good at.
The build default is 8192 MiB. dankclaw is memory-tight (frank-large's
70 GiB GTT plus the rest of the stack) and Gemma4 runs fully on the 3090
(-ngl 999), so the CPU-side cache is not the hot path. Cap it at 2048 to
give back ~6 GiB of LPDDR. Gemma4 is not a DeltaNet model, so the
>12.8 GiB CACHE_RAM floor does not apply.
Wired through frank-small.env (CACHE_RAM) -> serve-frank-small.sh
(--cache-ram), with a wiring seam so the cap cannot be silently unwired.
Each section's panels fill an auto-fill row (as many per row as the
viewport allows) and the sections stack vertically — the side-by-side
column layout was the wrong read of 'render the sections horizontally'.
The board rendered vertically for a user whose browser had cached the
pre-sectioning style.css: deploys overwrite /srv/homepage in place, and
nothing told the browser to revalidate. The @home handler on the post-auth
listener now sends Cache-Control: no-cache, so every load is an ETag
round-trip (a cheap 304 when unchanged) and a deploy is always visible on
the next navigation.
Frank
