This engine ignores SIGTERM: after systemctl stop its container sits in podman ps
state 'Stopping' for 20+ minutes WHILE STILL ANSWERING /health with 200. So a liveness
probe is a lying oracle for a window restore — twice a restore reported PROD HEALTHY
while systemctl is-active said failed and the runtime mask was still in place, because
the old container was still serving.
Records the conjunction the restore must verify (is-active == active AND is-enabled ==
enabled AND no /run/systemd/system/<unit> mask symlink AND the container is owned by
the unit and not Stopping) and the four-step repair recipe (mv the runtime mask away —
it survives stop and blocks start; daemon-reload; reset-failed — a failed unit refuses
to start; podman rm -f — podman stop hangs on the same SIGTERM).
Also records the overlap hazard: a later job's 'podman rm -f glm-probe' cleanup
deleted an in-flight job's container, so one compile round produced no evidence at all
('no container with name glm-probe found'). Check proc:// for running jobs before
opening a window.
tests/run.sh: 362 seams pass.
Root-caused the moving failures: they were my own scratch launcher. Its compile
branches were restructured and the '-e VLLM_COMPILE_FULLGRAPH=0' line was dropped, so
four consecutive boots mounted the wrapper patch while _FULLGRAPH still defaulted to
True — and with fullgraph=True EVERY break is an error, so each boot reported whichever
break came first (cell -> workspace -> compiler-disable). I had blamed
TORCH_LOGS=graph_breaks for the difference; that was wrong, the flag only logs. The
launcher sets the env var again, and patch 04's header, the runbook and the work log
now carry the true run history as a table instead of the bad theory.
New artifact: scripts/patches/glm53-compile-05-workspace-acquisition-opaque.patch —
the indexer acquires its shared workspace INSIDE the forward (its profile-run branch
literally says 'Reserve workspace for indexer during profiling run'), and
v1/worker/workspace.py:_ensure_workspace_size reads ContextVar/ubatch state, which
dynamo cannot trace. Wrap both call sites in a torch.compiler.disable'd helper
(narrower than decorating the workspace manager, which every model would go through;
a no-op when not compiling).
All five artifacts verified against the pinned image: applied in sequence with patch
-p1 they reproduce their recorded patched sha256 exactly (6e9cb81b…, 0751852e…,
732363bb…, 84969993…, c154115a…).
tests/run.sh: 362 seams pass.
Working the dyno name-map blocker one step at a time, with the tools to see it:
- All four patch artifacts are now genuine diff -u patches (they were prose + pseudo
hunks before, useless to patch(1)). Verified against the pinned image: each applies
clean and reproduces its recorded patched sha256 (6e9cb81b… / 0751852e… / 732363bb…
/ 84969993…).
- New: scripts/patches/glm53-compile-04-fused-qkv-rmsnorm-optout.patch — takes GLM's
MLA block off the fused-norm JIT kernel (R4D_GLM_FUSE_QKV_RMSNORM=0; the flag is
already a constructor arg glm5next sets at attention.py:583). Reason: in
models/common/ops/fused_qk_rmsnorm.py the kernel object is bound at line 223, AFTER
its use at line 211 — the launcher family (@kernel_launcher, 39 call sites) is what
breaks dynamo's break analysis.
- New diagnostics, both reusable and recorded: TORCH_LOGS=graph_breaks +
VLLM_USE_AOT_COMPILE=0 to name each break with its user stack, and
/home/dank/dynamo-probe (sitecustomize.py on PYTHONPATH, VLLM_DYNAMO_DUMP_ATTRS=1)
to print the dynamo name-map miss detail. Gotchas: a .pth on PYTHONPATH is NOT
executed, and the scratch launcher reset ENVARGS (now ${ENVARGS:-}), which silently
dropped env vars and wasted a boot.
Measurement discipline correction: I first recorded the 'Read uninitialized cell' and
'Unsupported method call' failures as fatal blockers. They are not established as
such — they appear only when TORCH_LOGS=graph_breaks is set, while a flag-free
break-tolerance run gets past break handling and dies on the name-map KeyError. The
likely mechanism is that graph_breaks logging makes dynamo build a break
*explanation*, and that analysis itself trips on the uninitialized cell. Patch 04's
header, the runbook and the work log now carry the confound explicitly rather than
the overclaim.
tests/run.sh: 362 seams pass.
DFlash2: fetched incoai/GLM-5.3-Flash-DFlash2 (2,342,169,800 B, sha256 matches the
Hub LFS oid) and tried --speculative-config {"method":"dflash","model":"/draft"}.
Config and drafter are accepted; the worker dies with 'Model does not support
EAGLE3 interface' - so the only gap is the target-side aux-hidden-state contract
(set_aux_hidden_state_layers + per-layer capture + the two-value forward return,
as deepseek_v2.py demonstrates twice in this image). Recorded the exact interface,
the GLM-specific unknown (what the single-stream state entering layer k means for
an mHC multi-stream trunk) and the honest expectation: no speedup on a
token-proportional pointwise bound.
fp8 KV: recorded the deciding measurement - the fork's KV reserve model is
dtype-blind (the fp8 boot printed the identical 1760 MiB / 13600 B-per-token plan),
so fp8 cannot buy capacity even if the gfx12 MLA path were rewritten. Verdict: do
not spend effort there.
Compile blocker narrowed from 'a latent GLM bug' to dynamo's name map: the
KeyError is thrown by torch/_dynamo/output_graph.py's nn_modules lookup (:3000,
registered :1259/:1384, _modules[..] prefixes stripped :1225), i.e. the compiler
cannot resolve a submodule by name while tracing the decoder layer. Next step is
TORCHDYNAMO_VERBOSE=1, with the note that the scratch launcher resets ENVARGS.
tests/run.sh: 362 seams pass.
A torch-profiler kernel-time window (496 decode tokens, rank0 trace parsed for
device-activity time) on the deployed GLM-5.3-Flash shape falsifies this page's
own "the expert gather is the bound" explanation:
46.18 s of kernel time / 496 tokens = ~93 ms per token (actual step ~104 ms)
34.8 % vectorized_elementwise_kernel 708,500 launches (1,428/token)
10.0 % r4d_gemm_moe_w4a16_nt_b16_m64 (the MoE GEMM)
6.7 % elementwise_kernel_manual_unroll
6.4 % wvSplitK_hf_sml_ (split-K GEMM)
8.9 % router: sbtopk + warpMergeSortTopK + bitonicSortKVInPlace
6.5 % r4d_mhc_* (hyper-connections)
1.05 % r4d_moe_lru_gather_kernel <-- the retracted suspect
The earlier arithmetic was circular (it assumed the gather consumed the whole
step). The real bound is unfused pointwise glue: the fork compiles its own Qwen
trunk (support_torch_compile in models/qwen4_exp/amd/model.py) and not its GLM
trunk, so the engine boots with "provides neither a compiled submodule nor
breakable CUDA graphs. Overriding to FULL_DECODE_ONLY." That also explains why
MTP4 measured flat — pointwise cost scales with the token count, so spec decode
amortizes nothing here — and it retires arena/hit-rate tuning (the gather is 1 %).
Staged as documented patch artifacts (not wired into any serve script; the
engine does not yet boot with them) — scripts/patches/glm53-compile-0{1,2,3}*.patch:
-01 models/glm5next/common/model.py decorate Glm5NextModel (R4D_GLM_COMPILE)
-02 model_executor/kernels/r4d_lib.py freeze 10 capability probes that do
os.path.exists/.so lookups inside the traced forward. functools.lru_cache
does NOT protect them: dynamo re-traces the wrapped body even when warm
(verified in-image); a plain module-global read compiles.
-03 compilation/wrapper.py make fullgraph=True opt-out, because
suppress_errors does NOT cover graph breaks and this trunk can never
satisfy fullgraph (indexer metadata syncs to host — .item() at
glm5next/amd/sparse_indexer.py:263,419).
With all three the trunk traces (Dynamo bytecode transform time 1.08 s) and dies
on KeyError: in_proj_qkvbfg_a in the mHC/KDA path — a latent bug the compile
exposes, and the remaining blocker.
Also records two structural constraints: no new HIP kernels are possible (r4d.so
ships without sources), which binary-blocks the fused router at GLM's 288
experts; and DFlash2 for GLM is a TARGET-side port, not a drafter port
(incoai/GLM-5.3-Flash-DFlash2 is architectures ["DFlash2DraftModel"] +
model_type qwen3, already mapped at registry.py:636; glm5next lacks only the
aux-hidden-state plumbing deepseek_v2.py demonstrates).
Runbook frontmatter, intro, mermaid and wall section, AGENTS.md and the work log
corrected to match the measurement. tests/run.sh: 362 seams pass.
Two operational facts the cutover surfaced: PYTORCH_CUDA_ALLOC_CONF=
expandable_segments:True is part of the qualified shape (the plan fills VRAM to
its modelled headroom, so the default allocator's fragmentation fails
profile/graph capture — measured on the deployed unit), and the deploy's e2e
gate drives the admin open-links spec, which walks every guarded vhost
including 192.168.0.112:8989 on FrankBook-Pro — a sleeping Mac mini fails that
spec and reports DEPLOY INCOMPLETE while the engine is healthy.
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).
PORTMAP=7773:7770 hook; health 200 on 127.0.0.1 and 192.168.0.235,
decode through the published path in band. 7773 chosen over 7770
(frank-primary owns 7770 when it returns). Log bullet recovered from a
misplaced insert into the 2026-09-28 cleanup section.
Repo tag qwen-fp8-tuned-20260929 at f532e03; serve script launches the
tcclaviger image by digest sha256:da402966... (local alias
qwen-fp8-runtime:tuned-20260929) — the floating :latest is no longer
referenced.
Source reading in the qwen-fp8 container: glm5next is registered with an
amd/ backend dir + DSA indexer; r4d.so has native moe_dsfp4/moe_dsfp4_mt1
entries (has_dsfp4()==True), so the old 'MXFP4 = emulation, missing
kernels' verdict is dead for this fork. DSFP4 = MXFP4 weights + DeepSeek
activation law. Offload recipes exist for mxfp4 and W4A16 (R4dW4a16MoEExperts
in offloader/expert.py:114). GLM gate is now the payload format
(compressed-tensors MXFP4/W4A16, none public) + a HIP boot probe.
The KV trim is inert: arena identical (5,648 slots) at 4.5 and 4.03 GiB
(planner buckets; the trim went to margin). Final 256k config
MAXLEN=262144 KV_BYTES=4328521728 prefetch off; full-speed alternative
MAXLEN=184224 at 3 GiB.
Asked for iterative decode/prefill improvement at a 32k working point
without touching the model or the quantization. There isn't one: gufo's
served settings are already at this engine's tuned point, so no config
change was made and none is proposed.
Measured on the repo's own prose and shell sources at 32,762 prompt
tokens, salted per run against a warm prefix cache, 3-5 repetitions:
* --prefill-chunk 512 -> 8192 moves prefill 410.7-412.4 t/s. A 16x change
in chunk size, 0.4% out. The lever is dead at this depth.
* --draft-tokens 5 -> 10 gives 13.79-15.86 t/s decode, all inside the
run-to-run noise. The 5-rep confirmation REVERSED the 3-rep leaders:
dt9+chunk4096 looked best and came last (12.86), the deployed config
came first (14.71).
* --draft-policy fixed vs adaptive: no effect. --min-draft-tokens:
rejected by the engine ("DFlash2 requires ... 1"). MTP: unsupported for
Q8 targets (token_embd.weight is Q8_0).
* --context 262144 -> 40960, tested as a diagnostic: no gain, and it
would break models.yml's declared contextWindow. Not shipped.
What does move the number is speculation itself — 6.65 t/s off vs ~15 t/s
on, 5.3x — and it is already enabled.
The two traps that cost most of the wall time are now in AGENTS.md's
benchmarking policy, because both produced FALSE results:
1. gufo bench cannot rank speculative settings and inverted the ranking.
Its corpus reports acceptance=0.933 +/- 0.000 with an identical trace
sha256 across draft widths — the same highly-predictable text every
run. It reported 29-37 t/s where real traffic gives ~15, and made
dt16 look 6% faster than dt7 when real text made it 14% slower.
2. A live A/B needs >=128 generated tokens. At 8, inter_token is
first-token noise; the first pass produced a nonsense ordering that
the 128-token pass reversed.
Plus the Server-Timing header is `ttft;dur=402.485` — the unit rides in
the NAME half, so splitting on "=" keys the dict "ttft;dur" and every
lookup silently returns nothing. Four configs reported "no Server-Timing"
while the header was present on all of them.
The disk was at 93% with 137G free. Nine retired payloads are now moved
to ~/.AGENTTRASH/20260928-retired-models/ with a MANIFEST.md giving a
restore command per item — moved, not deleted, and nothing is freed until
the purge is approved. Every one maps to a runtime already retired in the
runbook index.
Only the .gguf was taken from Qwen3.8-27B-UD-Q8_K_XL/: the live
frank-large DFlash2 drafter lives in that directory and stays put. The
manifest warns against restoring the directory wholesale.
Kept: checkpoints/ (23G) — unreferenced by the repo, but ComfyUI is live
and its workflows were not searched, so it is not confirmed dead. Also
logs/, because x4e-run.log is a SPARSE file (3.3G apparent, 4K real) and
frees nothing.
The reference check caught a live bug: serve-frank-small.sh's fallback
MODEL_DIR still pointed at the retired GSQ-RCO payload frank-small served
on 2026-09-16/17. frank-small.env has always overridden it, so the drift
was invisible — but a missing or unreadable env file would have turned a
config problem into a "missing asset" naming a model that is no longer
there. Repointed at Gemma4-12B-QAT/, which the env file already sets.
Not taken, by request: podman images (279G reclaimable, 95%) and the
uv+pip caches (73G). Together 352G of regenerable garbage, larger than
what was reclaimed here.
The 29.3G payload rollback target went with the rest, so the payload-only
rollback is now a re-fetch first; the runbook and AGENTS.md say so.
The target moves from unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL to
ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF's UD-Q8_K_XL —
an abliterated fine-tune of the same base, under the non-OSI SWIFT OPEN
LICENCE 1.0. Port, alias, context, drafter and client contract are
unchanged.
Compatibility was settled from the GGUF headers before fetching anything:
both files parse to the same architecture (qwen35), the same 866 tensors
with identical names in identical order, zero per-tensor ggml_type or dim
mismatches, and the same MTP head. Two metadata differences that look
alarming are no-ops, confirmed against gufo's source — general.file_type is
deliberately not consulted (the file gufo already served records Q4_K_M
while containing no Q4_K tensor), and Swift's extra
qwen35.attention.recurrent_layers key is never read; layer kinds come from
full_attention_interval, which both files carry as 4 and which agrees.
The load test agreed: 9.2 s to listening, 66.5 GiB of the 116.7 GiB iGPU,
no loader warnings, and a green contract battery including a two-turn tool
loop.
The DFlash2 drafter did not move, so the payload is now two files in two
directories: DRAFTER_DIR is its own tunable. That broke the deployer's
stray-run sweep, which keyed on the target filename and would have stopped
matching — a stray run would then have held 7770 past the port gate. It
now keys on the drafter, which every frank-large command line carries.
The fetch script sends no auth header: the repo is public, and a token on
the curl command line is world-readable via /proc/<pid>/cmdline. The
anonymous transfer ran at 1.8 MiB/s; the host token through a mode-600
curl -K config reached 7 MiB/s.
Test seam: the mutation pass found four real gaps. Two fetch assertions
were satisfied by a header comment rather than the URL assignment, so
repointing a repository left them green, and nothing bound the env's
MODEL_FILE/DRAFTER_FILE to the filenames the fetch scripts download. Both
are now explicit. A harness bug worth recording: a bats --filter that
matches no test reports zero "not ok", indistinguishable from a mutation
that survived — the harness now checks the 1..N count. 16/16 caught.
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).
Live numbers from the 2026-09-28 deploy: 13 s load to listening, RSS
30.6 GiB, ttft 549.8 ms / inter-token 24.2 ms on a short prompt, and a
green contract battery (health, ready, /v1/models at 262,144, content +
reasoning_content, tool_calls, SSE, and a two-turn tool loop).
Also recorded: gufo accepts every request field the harness sends in
extraBody and the full reasoning_effort set, both verified 200 — which
is why models.yml's reasoningEffortMap fold is now optional rather than
required, and why it is being kept anyway.
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.
Answers Frank's question: given the 2x R9700 box, which of DeepSeek-V4.1-Flash,
MiMo-V2.6-Flash-MOPD and GLM-5.3-Flash runs best, on what runtime, and can
Affinity / vllm-radiance / FreeToken-AMD be modified to run them fast.
Sizing, measured from the HF API rather than the model cards:
- DS4.1 payload 475.27 GiB, of which 189.13 GiB is Engram (two 94.56 GiB
shards, the layer 1 and 14 lookup tables). Lucebox never maps them, so
they do not evict the expert page cache.
- 240 routed experts x ~11 MB per token at the 37-of-384-per-layer residency
the hot stack can hold = ~2.4 GB across PCIe per token. At 55 GB/s real on
Gen5 x8 that is a ~23 tok/s ceiling, under the 35 tok/s goal before any
attention or dense work.
- The backend refuses layer-major prefill for V4.1, so the only legal
prefill is token-by-token; 1000 t/s is ~20x away.
Affinity (Codeberg StillDeadcode) builds clean here (hipcc 23, gfx1201, zero
errors) and claims 110 tok/s for the 284B V4-Flash, because the 101 GiB
container leaves the cold expert set in a pinned host pool in RAM. V4.1 is
2.5x too big to repeat that. Port scope, from both checkpoints' real
safetensors indices: expert machinery ports unchanged (identical tensor
naming, 15,360 tensors at 40x384), 26/32 per-layer tensors and 34/35 config
keys present. Five gaps - Engram, the disjoint {0,1,2} vs {0,4,128} ratio
vocabulary, CED, the DSpark draft geometry, vision. num_hash_layers is the
only key V4.1 lacks, so model.h:36's default of 3 silently survives and
would route layers 0-2 through a table that does not exist.
Also corrects: Dankserver RAM 60 -> 246 GiB (stale since the 2026-09-20 board
swap) and storage; the top-level index credited V4.1 with V4's geometry
(43 layers / 256 experts vs the actual 40 / 384).
New ACTIVE runbook (setup/doctor PASS=34/FAIL=0, UVA transport verified
in serving workers, wire-verified alias/reasoning/metrics), index +
vault entries flipped: llama.cpp b11030 endpoint RETIRED 2026-09-27 to
rollback target. Topology diagram updated.
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.
Instrument the live server to answer "can -ot target the most active
layers": AMD IBS op sampling on llama-server during 4 mixed concurrent
generations, sampled load addresses mapped through /proc/<pid>/maps to
backing tensors with extents derived from consecutive GGUF header
offsets (no quant type-size tables - a wrong per-element size silently
mis-buckets tensor tails, first run lost 59% of expert samples to a
junk bucket).
Measured (75 s window, 2.7M expert-tensor samples): per-block read
volume is FLAT, 0.93x-1.08x of mean across all 40 CPU-resident blocks.
MoE top-k routing fires every block every token, so "most active
layers" do not exist at -ot granularity - any 8 GPU-resident blocks
are equivalent, the lever is COUNT, already at the 5/3 VRAM ceiling.
Real skew is per-EXPERT (top 10% of 48x512 cells carry 40.5% of
samples), below tensor-override granularity. No config change.
scripts/frank-primary-expert-activity.py: dump + sample + analyze in
one entry point; --analyze-only re-analyzes saved samples. Instruments
production serving in place; not a benchmark.
29,696 B/token ctx-scaled (12 of 48 layers carry KV - full_attention_interval=4;
indexer and draft KV included); weights/RS/compute are ctx-independent.
262k = 18.75 GiB total / 9.37 per card; 100k = 14.3 / 7.1. Parallel
slots split the pool rather than multiplying it.
Battery 6/6: alias, reasoning_content, tool_calls, vision (probe image
described exactly), reasoning_effort high -> 200. Decode 11.8 t/s at
depth-0 prose (draft 109/accepted 72), 0.864 mean len 2.73 on tool
traffic. VRAM 29%/36% (output-head card carries the drafter). Also
records the ROCm1 drafter law in the runbook body (borrowed output.weight
+ n_copies==1 abort) and the two cutover traps: foreign-process health
false green, and llama-server SIGTERM cleanup hang.
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.
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.
Each LLM card now carries a details object (role/spec/use) rendered as a
bold pale-green role, a bright-green spec line, and a dim 'Use:' line.
app.js descHTML() falls back to the plain description for non-LLM cards;
new .desc-role/.desc-spec/.desc-use CSS + bare-mode reset.
Roles made neutral (no nicknames): frank-large = deep reasoning,
frank-medium = primary model, frank-small = fast utility model.
The /docs model guide was fixed — it had drifted to retired model info
(frank-large as Qwen3.8-Flash-Next 87.3 GiB/200k, frank-medium as FP8
~31 GiB) — now Qwen3.8-27B UD-Q8_K_XL 31.5 GiB/262k and MXFP4/W4A8
19.4 GiB, reordered large->medium->small. bats 30/30 + live render.
The auth works via the modern /Users/AuthenticateByName endpoint (what the
web UI uses). The 401 was a test artifact from probing the dead legacy route.
No config change needed; LDAP-Auth plugin + authentik 2026.8.3 outpost healthy.
The UserWriteStage writes prompt_data['password'] via user.set_password().
A PasswordStage only authenticates the current password. Document the
correct mechanism (password field on the default-user-settings prompt +
empty-password guard policy) and the throwaway-user verification.
The default-user-settings-flow was missing a PasswordStage, so users could
edit name/email/locale but not their password. Added a PasswordStage
(InbuiltBackend) bound at order 101. Documented the flow's stage table and
the two ORM gotchas (MTI through model, required backends array).
The local username/password path is retired (ENABLE_LOGIN_FORM +
ENABLE_PASSWORD_AUTH false, ui.enable_login_form DB override false) and
qa-e2e-admin is out of the authentik Admins group. Documented in the SSO
section and History.
Records the LDAP-Auth plugin wiring: the Jellyfin LDAP provider +
outpost on Dankclaw, the svc-jellyfin-ldap service account, the
jellyfin_users/jellyfin_admins access groups, and the key gotcha that
the bind credential is a PASSWORD (set via Recovery), not an API/app
token — the default auth flow's standard-password backend rejects
tokens with 'flow error password: Invalid'. Verified end-to-end:
alex (in jellyfin_users) logs in with their authentik password and the
plugin creates the matching Jellyfin user.
Boot 2026-09-22 at 0.98 fill: KV pool auto-sized to 425,047 tokens (1.62x
the 262,144 window) with 14.42 GiB per card available for KV. The DFlash2
drafter on the Swift finetune measures mean acceptance length 7.00 / 85.7%
(easy) and 5.08 / 58.3% (varied) — it survives the base-model change.
Replaces the estimated ~420k / ~17.6 GiB figures with the measured values.
0.99 failed the vLLM startup memory check before weight load: the R9700
reports 31.86 GiB total but only 31.23 GiB free at device-init (the ROCm/HIP
context + NCCL + radiance custom all-reduce consume the 0.63 GiB gap), so
0.99 (31.54 GiB) exceeded free and the container crash-looped. 0.98 (31.22
GiB) is the ceiling and the prior production value.
Also fixed the runbook KV math that had shipped with the 0.99 change: the
~730k pool estimate was impossible (MXFP6's 25.16 GiB weights > MXFP4's
19.37 GiB, so the pool is smaller, not larger than MXFP4's 486k) and the
34.2 GiB/card figure was not the R9700 total. Recomputed ~420k tokens at 0.98
fill.
Comrade Chief Designer
Frank