Context: 262144 was measured before it was deployed -- 24.72 GB on GPU 0 and
29.14 GB on GPU 1 of 34.21 GB each, ~5 GB of headroom on the busier card, and a
140,069-token prompt prefilled through the single slot in 134 s to prove the
window is real. The 114688 wall was the vLLM predecessor's arithmetic, not this
runtime's.
Throughput, measured through the service: 1.0-1.4k tok/s prefill from 4k to
140k, 43.8 tok/s decode on a 512-token generation, 41-71 % DFlash2 acceptance,
and the prefix cache re-prefilling 4 of 998 tokens on a repeated prompt.
The signals move with the runtime, so the fleet's rules and dashboard are
re-cut rather than renamed: vllm: series do not exist any more, and two of the
old rules watched things llama.cpp does not export at all (KV-pool fill, p95
latency). Those are retired with the reason written down, and LlmSpecDecodeOff
takes one of the slots -- a lost drafter is the failure no client can see. The
observability seam now fails if any rule names a series the endpoint does not
export, which is what would have caught the stale vllm: expressions.
omp models.yml (outside the repo) is updated in the same pass: contextWindow
262144, and the full reasoning-effort map, because Qwen3.8's template answers
500 on 'high' -- verified against the live endpoint, low/medium/xhigh answer
200. Subagents run at high.
halogen-flash-server is ACTIVE again with its 2026-09-16 measured ledger (budget
33.5 GiB against a need of 27.2 — no clamp — and 14.7 GiB left for everything
else), ik_llama.cpp is retired with its measurements kept as the record of why,
and the new frank-small runbook covers the -mtp file, the 64 KiB/token KV
arithmetic, the MTP contract, and the reasoning_effort trap that cost me every
subagent on the endpoint.
AGENTS.md: topology, Active Services, runbook index, and three new llama.cpp
lessons (MTP is a property of the file; --jinja is what `tools` needs; a model's
template can reject the harness's thinking level). Three pre-existing defects
found while editing it: a truncated sentence mid-file, a harness path that does
not exist on either server, and the benchmarking stop/mask recipe still calling
frank-large a root unit.
Truthfulness notes worth keeping: the co-tenant stall NOTE prints again, so the
claim that it "no longer prints" is gone and the three observed block counts are
recorded instead of a guessed threshold; and the Observability page says out
loud why frank-large has no scrape job rather than leaving a silent absence.
New page: LLM/Dual-R9700-Cooperation.md — registered in the vault index, with
the measured evidence rather than the theory.
**The answer.** Card #2 sits behind the B650 chipset, whose bridges advertise
`AtomicOpsCap: Routing-` (read-only), so ROCr refuses to fill the hostcall
buffer RCCL's kernels declare and no RCCL op can dispatch on it. Two paths fix
it: an M.2→PCIe x4 riser into the free, CPU-attached M.2_2 slot (~$30; per
ASUS's spec page M.2_1 and M.2_2 are CPU-attached, PCIEX16_2 is chipset in x1
mode, and there is no x8/x8 bifurcation on this board), or a board whose CPU x16
bifurcates to x8/x8. Bandwidth is not the constraint: ≈10 MB per token-step ≈
1.4 ms at Gen4 x4.
**New measured results.** A bare 2-rank torch.distributed run: rank 0 (CPU-lane
card) passes broadcast/all_reduce/barrier; rank 1 (chipset card) fails all
three, and `send`/`recv` fails too — which kills pipeline parallelism as an
escape, since vLLM's PP handoff is exactly that primitive.
**Correction.** I previously said no software path exists. That overshot. One is
open and unverified: recompiling RCCL so its kernels stop declaring a hostcall
buffer (`-mprintf-kind=buffered` is the claim). Counter-evidence recorded: RCCL's
device source contains no live printf/assert/__assertfail, so the trigger is
unexplained, and the claim traces to search summaries, not a primary source. The
page carries the two-command test that would settle it. Also corrected: 0.9.3 is
radiance's version, not vLLM's — the base is vLLM 0.27.1 / torch 2.11.0 / ROCm
7.14, and its shipped RCCL exposes no `ncclDevComm*`, so torch's symmetric-memory
path cannot run.
**Rule added to the benchmarking policy**: it covers ANY GPU experiment, not just
benchmarks — including a bare 2-rank probe. Running one against the live service
on 2026-09-16 preceded the host going hard down (no ARP, no ICMP, power cycle
required); a hung AQL dispatch wedging the driver is the plausible mechanism.
The policy also now says how to tell off from wedged: `ip neigh` from a peer.
Retiring dankclaw/compose.yaml and adding alert rules invalidated claims across
the repo, including in the rule file agents read first. Clean cutover includes
the prose.
**Tests that had gone hollow.** Four assertions grepped dankclaw/compose.yaml
for a service name. With the file gone they passed by *absence* — a gate that
can no longer fail. Each now asserts the real invariant ("no dankclaw compose
file competes with the quadlet units") and keeps a live check for a re-added
entry, so it still fails when one appears: verified by recreating a compose file
with a comfyui service and watching three tests go red, then removing it.
**AGENTS.md, which was wrong about ComfyUI.** It said ComfyUI runs CPU-only
("no ROCm wheels for gfx1151, CUDA images wrong"). That was true in the
compose era and is false now: the restored unit runs with /dev/kfd + /dev/dri and
must NOT pass --cpu. An agent trusting the rule file would have re-broken it.
Also corrected: the observability paragraph ("RUNNING BUT UNCONFIGURED, no
datasource, no rules" — all three have been configured since 2026-09-16), the
Active runbook row that still named halogen for frank-large, halogen's absence
from the Retired table, the benchmark policy naming halogen's harness, and the
seam list.
**Unit and page claims.** prometheus.container said "no alerting rules anywhere
in this stack"; node-exporter.container said Dankserver runs from its compose
stack; Prometheus.md documented three jobs as working (they scrape HTML: they
can never report up) and said no dashboard existed; index.md and the three
authentik service pages pointed at the retired file; Authentik.md's upgrade
instruction told you to bump an image tag in it.
One bad edit of my own on the way (a stale line number clobbered a See Also
entry in Prometheus.md) — caught by reading back, fixed, and the vault link
checker now proves the cross-references hold.
The two replicas behind :7770 were on plain round-robin, which throws away
prefix-cache hits: an agent loop re-sends its system prompt and file context
every turn, and alternating replicas means every other turn pays a cold
prefill. Measured with 90k-token contexts, warm-turn TTFT was 2676 ms.
Pinning everything to one replica is not the answer either — a cold batch
(the shape a benchmark or a burst of parallel subagents produces) then loses a
card's worth of prefill: 16 requests took 30.1 s pinned against 18.6 s spread.
So the policy routes by request shape. A continuation (more than one message —
the agent-loop signature) is pinned to the replica that served its prefix;
anything else spreads across the cards by counter. Measured: 19.97 s for the
burst and 1095 ms warm-turn TTFT — the best of both, without a regression on
either workload.
The policy lives in proxy/routing.py, separate from the HTTP plumbing in
proxy/affinity-proxy.py, so it can be tested without aiohttp, a network or a
GPU. tests/frank_medium_proxy.bats covers it, and it earned its keep: the
first version hashed fresh prefixes to pick a card, which sends every member of
a same-prefix burst to one card (29.8 s, measured), and a stale index in the
pin path returned 500 on every continuation. Both are now assertions.
ROUTING=roundrobin and ROUTING=affinity stay available to re-measure the
choice on this host; the default is adaptive.
The radiance MXFP4 stack cannot run TP=2 on this host. RCCL's collective
kernels carry a hidden hostcall-buffer parameter, and ROCr refuses to
dispatch them on a device without PCIe atomics: the AQL dispatch fails with
hipErrorIllegalState ("the operation cannot be performed in the present
state"), which is what every two-rank collective hit. The second R9700 sits
behind the chipset bridges 05:00.0/06:09.0, which advertise
`AtomicOpsCap: Routing-` — a read-only capability, so no software can enable
atomic routing on that path and the driver's
pci_enable_atomic_ops_to_root() fails for that card. The first card, on CPU
root port 00:01.1, has atomics enabled.
Ruled out: kernel version (7.0.0-28/-30/-31 identical, after a full upgrade),
iommu=pt, P2P hardware (45.3 GB/s between the cards), the shipped librccl (a
from-source rebuild reproduces the failure at the same call path), vLLM and
pynccl (a bare two-rank torch.distributed allreduce fails the same way), all
NCCL transport knobs, and single-rank tests (NCCL short-circuits at
world_size=1, so one-card success proves nothing).
Deployment: three rootless Quadlets — frank-medium-a (:7771, card 1),
frank-medium-b (:7772, card 2), both TP=1 at 114688 context (262144 and
131072 do not fit one card's KV) with vLLM-profiled KV — and
frank-medium-proxy (:7770), a round-robin that preserves the fleet contract
of one endpoint and one served model name. frank-medium.container stays as
the TP=2 target for a host whose second card is atomic-capable; the deploy
handler does not install it and trashes any stale copy.
Measured through the proxy (vllm bench serve, random dataset, --ignore-eos):
conc 1 42.8 tok/s, conc 4 147.6 tok/s, conc 8 230.8 tok/s, 32k prefill at
~2.8k tok/s per card, TPOT p50 23.6-28.8 ms.
Also: healthcheck reads PORT so one probe serves all three units, the hermes
example and the harness models.yml drop to the real 114688 context, and the
runbook records the full evidence chain.
- Runbook with the measured envelope (prefill ~192 t/s at the VNNI ceiling;
decode ~3.8-4.3 t/s gated by 100 backend splits/token, GPU 95% idle), the
root-cause evidence chain, tuning levers, and co-tenancy traps
- AGENTS.md: fleet topology row + Active Services section for the ik
deployment; halogen demoted to rollback; bench policy unit type fixed
- LLM + root indexes relinked (frank-large-ik-uncensored ACTIVE,
halogen-flash-server retired)
New runbook page serverAppConfigs-docs/LLM/frank-medium-rocmfpx.md records
the hardware swap, the self-contained gfx1201 build, the measured layer-vs-
tensor decision (llama-bench multi-device syntax gotcha included), the
tensor-mode draft abort, served-path numbers, and the post-cleanup host ROCm
posture. AGENTS.md, README, docs indexes, Dankserver System Specs,
deployment/Hermes/OpenWebUI/Plex/Stack pages follow the rename;
freetoken-frank-small is marked RETIRED and kingjones-q8agent SUPERSEDED.
Work log entry added.
Predicted ~10.8 GiB KV / ~33.4 need / ~10.5 host-left; the boot ledger
printed ~11.0 / ~31.5 / 100.0 GiB held with 9.1 GiB + 1396 contiguous
2 MiB blocks left. Stall NOTE no longer prints at this footprint. Also
documents the ~45-60 s first-request PING silence after a restart (the
healthcheck's HealthStartPeriod covers it; do not restart the unit).
The 09-12 doubled pool fit only at reserve 15, leaving 7.1 GiB / 310
contiguous 2 MiB blocks for the ~28 co-tenant containers and making the
engine print its minutes-long-stall warning on every boot. 401,408
positions (~10.8 GiB KV) hands ~3.4 GiB back while keeping MAX_TOK=32768
and reserve 15: modelled need ~33.4 GiB vs budget 38.5, so the fit check
should not clamp. Capacity becomes one full 262k conversation resident
beside a ~139k one, or three concurrent 131k chats (three slots).
Docs: AGENTS.md fleet table + halogen section, runbook flags table /
co-tenancy tense / admission-arithmetic paragraph updated for the trim.
Ledger confirms the change landed: "3 slot(s) over one 524288-position pool",
"slots: 1 -> 3 POOLED, 111.0 MiB each", held 103.5 -> 103.4 GiB.
Recorded the oversubscription nuance that the old row missed: the slots were
never the binding constraint on context. 4 x 262144 exceeds the 524288 pool,
so admission was pool-bound all along -- two full-length conversations, or
four at 131k. Lowering the cap trims simultaneous requests, not capacity.
Raised /swap.img from 8 GiB to 64 GiB on Dankclaw. Host-level state with no
repo file, so it was invisible to the repo until now: fstab line 12 drives the
generated swap.img.swap unit, ext4, fallocated hole-free, swappiness 60,
zswap off. 748 GiB still free on /.
The reusable part is the ordering. The old file held 4 GiB of live pages and
MemAvailable read 73 GiB while only ~5 GiB was genuinely free -- the pinned
model weights are counted as reclaimable page cache, so the headline lies by
the size of the model. Swapping off before the replacement is online would have
pushed those pages into RAM that does not exist. Creating and enabling the new
swap first let them migrate instead: swapoff took 65 s and the host never
wobbled.
New page serverAppConfigs-docs/Dankclaw/Swap Configuration.md, linked from
the index, plus a pointer in the AGENTS.md memory-model section so nobody
reasons about headroom without checking swapon.
Old 8 GiB file staged at dankclaw:~/.AGENTTRASH/20260912-swapfile-8g/
pending approval to purge.
Seven restarts measured. New section "The reserve cannot buy air": reserve 16
was deployed and held exactly what 15 holds — 103.5 GiB, 7.1 GiB left to the
host. The flag is a term in the fit-check inequality, not a reservation, so it
has only two regimes: below the pool's requirement it changes nothing
observable, above it the pool silently disappears.
Sizing rule now defers to the engine's printed requirement (budget >= 36.5 for
524288 at max_tok 32768, from "need ~35.0 GiB plus 1.5 of margin") over my
modelled 37.0, and the ledger table carries the reserve-16 row.
Ledger confirms the doubled pool is actually reserved (524288, 13312.0 MiB)
at max_tok 32768 with no clamp and no WARNING: 38.5 budget vs 37.0 needed.
Recorded the cost honestly. The server now holds 103.5 of 121.2 GiB and the
engine reports only 310 contiguous 2 MiB blocks / 7.1 GiB left for everything
else (24-reserve baseline: 2081 blocks / 12.1 GiB). All 28 co-tenants stayed
up, but the engine volunteers a new note: when memory runs out, frank-large
AND its neighbours "can stall for minutes at a time at full CPU with no disk
activity and no output, which is not a crash and needs no restart". That is
the least diagnosable of the three failure modes seen today, and `free` hides
it — MemAvailable still reads ~74 GiB because the pinned weights count as
reclaimable page cache.
Sizing rule now expresses the budget as a function of reserve, shows both
endpoints (24 -> 29.5, 15 -> 38.5), and the max_tok ceiling is labelled as
reserve-conditional (<= 18,130 at 24; <= 35,700 at 15).
Deployed HALOGEN_MAX_TOK=32768 by operator call (upstream default, full prefill
speed) and confirmed the prediction from the ledger:
kv pool: 524288 positions need ~35.0 GiB ... LOWERING THE POOL TO 262144 (~27.8 GiB)
memory: 68.0 weights + 7.2 KV pool + 21.1 working = 96.3 GiB in all
so the effective pool is 262144 again and the doubling this task set out to do
is not in force. Healthy, completion verified. Left the pool requesting 524288
deliberately: with KV_POOL_FIT on that is a grow-if-RAM-frees-up declaration,
not a mistake.
Two corrections to what I wrote earlier today:
1. The engine's sizing block, and its "WARNING even 262144 ... host RAM cannot
spare it" line, print ONLY when the fit check had to clamp something. The
09-11 baseline boot prints no kv pool: sizing lines at all. So the absence
of a warning in old logs was never evidence of headroom.
2. The budget needs a vision term. Actual need is pool + arena + 1.97 GiB of
vision tower, not pool + a 1.5 GiB nominal margin. That makes the ceiling
for a doubled pool max_tok <= 18,130 rather than 19,115, and it means the
32768/262144 corner this box has run in since 09-11 is ~0.3 GiB OVER its own
stated budget -- and has been the whole time. It boots and serves with
12-14 GiB genuinely free because the 24 GiB reserve is generous. A soft
floor, not a wall.
The arena model also reproduces upstream's three published "on the device"
figures exactly (35 / 42 / 41 GiB), confirming they are pool+arena totals at
the default max_tok and not pool-only -- which is the misreading that made the
doubling look affordable in my first estimate.
HALOGEN_KV_POOL_POSITIONS 262144 -> 524288, which is upstream's own
default (2 x HALOGEN_CTX). The old pool was the binding constraint on
concurrency, not context: a request reserves prompt + max_tokens against
the pool, so with pool == CTX four concurrent 65k chats were contending
for one full-length conversation's worth of positions. Two full-length
conversations, or four at 131k, now stay resident.
Cost is ~7.2 GiB more device RAM (measured 28 KiB/position), taken from
the page cache the 47.7 GiB n-gram lookup table reads through. Live
startup ledger for the prior config: 68.0 weights + 7.2 pool + 21.1
working = 96.3 GiB held, 12.1 GiB left on the host. The doubled pool
puts the remainder near 5 GiB against a ~4.3 GiB co-tenant working set,
and cache at ~69 GiB -- still above the lookup table, so the table can
stay hot. Compensating lever if long prompts start crawling:
HALOGEN_MAX_TOK=16384, which frees 8.3 GiB of prefill arena for ~8%
of prefill throughput.
Docs updated to match, including the admission-trap paragraph, which was
only true while pool == CTX.
The 2026-09-12 homepage outage slipped through because the live-fleet
Playwright suite was a manual 'MUST invoke' that deploys skipped. Wire it
into deploy.sh as the [3/3] gate: after a behavior-affecting deploy,
run tests/e2e/run.sh against the live fleet; a failure exits DEPLOY
INCOMPLETE. Add --skip-e2e as an emergency escape hatch. Update the
AGENTS.md deployment-completeness contract and flow diagram to match.
Verified: bash -n clean, --skip-e2e parsed, unknown flags rejected,
seam suite green (only the pre-existing comfyui test 73 fails).
Rewrites the [[Observability]] umbrella page and the five component pages for
what is actually deployed: rootless Quadlet units instead of compose services,
the loopback-only publish posture (node-exporter's LAN binding explained), the
loki healthcheck living in its image because the image has no shell, and the
Home=/root trap that killed the first grafana start.
Adds the note that matters most to a reader: the stack is installed, healthy
and UNCONFIGURED. Grafana reports zero datasources and zero dashboards with an
empty provisioning directory; Prometheus has no rule files and no Alertmanager;
Loki is configured but has no reader; node-exporter runs its default
collectors. Alloy is the only configured piece. Metrics and logs are collected
and retained, and nothing is visualized or alerted on.
AGENTS.md's boot-persistence gap note is replaced by the resolution.
Rebooting Dankclaw for the amd_iommu=off change exposed five services that
exist only as compose.yaml services with no Quadlet unit (prometheus, grafana,
loki, alloy, node-exporter): they did not come back and had to be restored by
hand. The boot-persistence rule already requires units for them; this records
the concrete gap so the next reboot is not a surprise.
frank-large moves from the kingjones30/ROCmFPX llama.cpp build to
peonist-ai/halogen-flash-server 0.5.8 serving Qwen3.8-Flash-Next (w4b
.hgn 115.55 GiB + quality overlay). Upstream measures this engine at
roughly 4x the prefill throughput of the llama.cpp family on the same
gfx1151 silicon, and prefill dominates any prompt with real context.
Shape: a rootless Quadlet container (dankclaw/frank-large/quadlet/),
engine on container loopback :8730 (never published), OpenAI front-end
:8731 published as host 7770, HALOGEN_MODEL_ID=frank-large so no client
renamed anything. Context 262144, KV pool 262144 positions (~7.2 GiB,
conservative for a shared 121 GiB host), 4 slots, host reserve 24,
vision tower on, weights pinned, all other flags at vendor defaults.
Weights are fetched by HALOGEN_DOWNLOAD on first start into a writable
/home/dank/models/halogen.
The llama.cpp era (unit, env, serve script) is staged in .AGENTTRASH/
rather than deleted; the STRIX payload and the ROCmFPX build stay on
disk as the rollback target. deploy_llm_large becomes a user-quadlet
handler: it retires the old ROOT unit (moving its checkout symlink into
the home trash, never rm) and gates the first start on the download
rather than reporting a failure for a fetch that is working exactly as
designed.
frank-npu is retired in the same change. The kernel cmdline moves from
iommu=pt to amd_iommu=off for the 13-16% of prefill upstream measured,
and that takes the XDNA2 NPU with it: without PASID/SVA the driver
cannot open /dev/accel/accel0 (err=-19). Its five dependent routes are
repointed (Hermes vision -> frank-large, Hermes title generation ->
frank-small, harness vision -> frank-large, tiny -> frank-small, task ->
frank-large:medium) and its provider blocks are removed from both the
harness config and Hermes's live config. Audio input leaves the fleet
with no replacement; image input survives on halogen's vision tower.
Docs: new halogen-flash-server runbook, new IOMMU decision record, and
frank-npu rewritten as a retirement record. AGENTS.md topology, runtime
sections, benchmarking policy (frank-large is a user unit now) and the
harness model-config section are corrected.
FrankBook-Pro becomes the only *arr/qBittorrent deployment. Every fleet
container (qB + five arrs) now shares gluetun's netns, so all egress —
torrent, indexer APIs, metadata lookups — exits the WireGuard tunnel by
construction (AllowedIPs=0.0.0.0/0); the arrs' own ports publish on the
gluetun unit, none on the arr units themselves.
- dankserver/compose.yaml: remove the six arr services (the Aug 20 compose
copy — never healthy, superseded; config dirs trashed on the host)
- dankclaw/Caddyfile + shared/homepage/services.json: arr vhosts and
probes repoint 192.168.0.235 -> 192.168.0.112 (FrankBook-Pro)
- frankbook-pro units: five arrs join gluetun netns (Wants/After/Network);
gluetun publishes 9696/8989/7878/8686/8787 alongside 8080/6881
- tests/frankbook_quadlet.bats: new VPN egress seam — every arr+qB unit
must share gluetun's netns and publish no port; gluetun must publish the
whole fleet's ports
- deploy-plan.py: gluetun changes carry the whole netns family (a gluetun
recreation kills all six joiners); dankserver compose set loses the arrs
- AGENTS.md: deployment is complete only when unit tests AND the Playwright
E2E suite both pass
Mechanical identity rename across the knowledge base, AGENTS.md, README, the
hermes config example, and homepage services.json. No behavior change; served
aliases on the LLM endpoints change with the deploy of commit 69f87c8.
Every Caddy-proxied service is now either behind the auth chain or
explicitly internal-only, with the provider-first flip procedure codified.
The comfyui GPU-access seam test now asserts the deployed contract
(group_add keep-groups + udev MODE 0666 on kfd/renderD*) instead of the
pre-fix 'video' group assumption.
Env file is the source of truth (unit ExecStart runs the serve script which
sources it); serve-script default and the deployer health-gate URL flipped in
lockstep so the post-restart health gate polls the new port. Docs, fleet table,
and both index bullets updated to match.
Prior docs claimed unknown tags silently serve llama3.2:1b. Live probes on the
live endpoint disprove it: /v1/chat/completions answers HTTP 200 with a flat
{"error":"Failed to load <tag> model!"} body and no choices; /v1/completions
answers a nested OpenAI-shaped server_error (code 500) under HTTP 200. Valid
tags route per-request to the named model (response echoes the requested tag);
no restart needed to switch between registry tags. Corrected in the runbook,
the AGENTS.md runtime section, the serve-script header comment, and the
historical FastFlowLM incident note.
frank-default-sightsound (FLM v1.0.1, XDNA2 NPU, port 52626) is live on
Dankclaw. Documents the first-deploy crash-loop root cause: iommu=off on the
kernel cmdline breaks the XDNA2 SVA bind (amdxdna_drm_open ret -19), so every
/dev/accel/accel0 open fails with ENODEV; fixed with iommu=pt + reboot.
Whole-registry single-port serving with per-request routing by exact FLM tag;
unknown tags fall back to llama3.2:1b (no 404). Health = GET /v1/version.
Vision + audio towers proven live (image_url color probe; audio control-pair
token-count probe). Updates AGENTS.md fleet table + runtime section, both
index pages, and the change log.
- kingjones-strix-rocmfp4 reactivated as the ACTIVE large runbook:
runtime build recipe (WEBUI=OFF gotcha), deployed serving profile,
fa-on-works-unpatched evidence, MTP heads documented unloadable,
swap procedure + 2026-08-30 validation record
- agentionai-fast-imatrix marked RETIRED (rollback record kept)
- freetoken-frank-default-small: model/lineage/template sections now
Huihui abliterated FP8; new operational quirk: chat API 422 without
explicit model field
- LLM index + AGENTS fleet table/runtime sections current; both
services' history chains fixed (small was still Tiel in AGENTS.md)
- worklog entry added; models.json contextWindow for large corrected
to the real per-slot 131072 (llama clamps n_ctx_train/parallel)
fa on aborted graph build: build_attn_qsa called ggml_fill on the
F16-converted kq mask (GGML_ASSERT F32 at ggml.c:5371). Patch mirrors the
MLA sparse path in llm_graph_context::build_attn (F32 base mask for the
top-k surgery, F16 cast only at the attention call, gated on
cparams.flash_attn). Vendored at scripts/patches/qwen4exp-qsa-f32-mask.patch
(sha256 f2f4a486...); the build-qwen38 binary on Dankclaw is rebuilt with
it and validated live at CTX_SIZE=32768 (health 200, real completion).
- Main model (v2 joined PLE layout, sha256 1e4160ca…) loads and serves on
build-qwen38 only with --flash-attn off: the QSA indexer path calls
ggml_fill on the F16-cast kq mask and aborts graph build (GGML_ASSERT
F32 at ggml.c:5371). Verified live: model loaded, health 200, real
completion.
- MTP draft head (agentionai FAST, 2.28 GiB) does not load on this binary:
qwen4exp loader requires full per-layer blk.<il>.hc_attn_norm.weight,
head carries only blk.48. Third confirmation (EasiiX Q8_0 + agentionai
FAST vs kingjones STRIX_LEAN previously, now own-matched pair). Spec
decoding runs ngram-mod only; head retained for a future compatible build.
- FLASH_ATTN=off and SPEC_TYPE=ngram-mod wired through env + serve script;
runbook and AGENTS.md updated with the verified constraints.
Model: agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF (87.06 GiB,
Q4_0_ROCMFP4_FAST imatrix-calibrated, per-head PLE table inside the GGUF —
fully VRAM-resident). Draft: agentionai/Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST
(2.28 GiB, matched ROCmFP4-FAST quant, ~66% acceptance at n-max 3).
Vision tower (f16) loaded via mmproj/.
Runtime: charlie12345/ROCmFPX build-qwen38 (HIP, ROCm 7.2.4, gfx1151) —
the only binary with the ROCmFP4 FAST types. Replaces the jcbtc CIRU v1.1
deployment (ciru-ai runtime).
Profile: card sampling table (temp 0.7, top_p 0.8, top_k 20, min_p 0.0,
presence 1.5) mixed with the validated build-qwen38 serving profile:
262144 ctx x 1 slot, b 4096 / ub 4096, t 16 / tb 16, f16 KV, fa on,
cont-batching, prompt cache + 8 GiB cache-ram + idle slots, 16 ctx
checkpoints (no --checkpoint-min-step — unsupported on this binary),
--fit off (auto-fit segfaults on qwen4exp hyper-connection config),
--spec-type draft-mtp,ngram-mod with n-max 3 (adaptive p-split measured
worse per author card), p-min 0.75. Qwen-Sharp chat template kept;
reasoning stays in DeepSeek format.
The 2026-08-28 failure of this draft head on the kingjones STRIX_LEAN
model was a cross-vendor pairing problem: the head carries
blk.48.hc_attn_norm.weight (verified in-GGUF, same shape as the working
CIRU draft). Docs: new runbook agentionai-fast-imatrix, index updates.
All in-repo path references (AGENTS.md, README, old scripts, report artifacts,
test code paths) rewritten in the same commit; focused-test map extended for
.gitignore, old/scripts/*, dankclaw/comfyui/*, and report/* per this repo's
own convention ('add one before committing'). Obsidian wikilinks are
title-based and unaffected.
A bare compose container dies silently at reboot (rootless Podman has no
boot-time auto-start; 'restart: unless-stopped' does not survive shutdown's
explicit stop). Rule established by the 2026-08-26 Dankclaw reboot, which
left Caddy down and Pi-hole crash-looping on a sysctl conflict.
Reconfigure to 3 parallel 160000-ctx slots (was 1 slot). KV cache is
now asymmetric: K at q8_0, V at q5_0, both with Hadamard. The 3 slots
triple the KV, so expert blocks 27-34 are pinned back to CPU (freed
~8.7 GiB) leaving output-adjacent 35-40 on CUDA. Q8_0 model,
split-mode none, spec disabled (ik limits spec to 1 slot). AGENTS.md:
drop the scratch-port rule (test/bench processes cannot share the
single GPU with the running service anyway). Env, serve script, bats,
docs updated.
- Place ik's Trellis (IQ*_KT), IQK (IQ*_K), MXFP4, and dedicated fast KV type
Q8_KV in a single high->low bits-per-value table with ROCmFPX TurboQuant KV.
- Mark mainline-provided types (*), KV-native vs weight-family-reused-for-KV.
- Hadamard annotated as a transform on top of a base quant, not a row.
- bpw read from exact ggml block structs (QK_K=256, fp16 scale): type_size x 8 / QK,
verified against the struct comment "6.5625 bits per weight" and the trait table.
Notes where legacy nominal figures (4.0/4.25) diverge.
- AGENTS.md: add benchmark directive (use llama-bench / vllm bench; ask before
rolling your own).
Fan out subagents to compare mainline llama.cpp, charlie12345/ROCmFPX,
and ik_llama.cpp, then add their findings to the project knowledge base:
- docs/Research/Llama Cpp Runtimes.md (positioning + quantization + server fit)
- docs/Research/Llama Cpp Code Diff.md (code-level quant diff, table, recommendations)
- docs/Research/SGLang.md (what SGLang is, comparison, our-boxes fit)
- docs/Research/index.md (Research progressive-disclosure index)
Cross-linked from docs/index.md (root) and docs/LLM/index.md.
AGENTS.md:
- Add Documentation Authoring section: docs/ is an OKF bundle; point doc authors
at the canonical spec in the system-config knowledge base
(~/.pi/agent/docs/references/okf-spec.md), not the orphaned
docs/references/okf-spec.md; consolidate read-index/one-concept-per-file/
progressive-disclosure/citation rules.
- Map AGENTS.md to docs_completeness.bats in the focused pre-commit hook (it was
last committed before the hook existed and had no mapping).
frank-default-large now serves the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT
model with a standalone MTP draft head (Q4_0), f16 K + TurboQuant V KV cache,
and the Sharp chat template. Context is maxed to 262144 (one slot); reasoning
is on with preserve_thinking + preserve_reasoning in the chat kwargs.
- frank-default-large.env: Q8_0 AGENT model paths, CTX_SIZE=262144, REASONING=on,
REASONING_FORMAT=none, CHAT_TEMPLATE_KWARGS {enable_thinking, preserve_thinking,
preserve_reasoning}
- serve-frank-large.sh: standalone draft-mtp profile (already switched off the
Kairic/PromptForge path)
- download-q8agent.sh: reproducible HF fetch of the three payload files
- docs/LLM/kingjones-q8agent-rocmfpx.md: Q8_0 AGENT runbook
- AGENTS.md: topology + ACTIVE runtime section + TTM/GTT load note
- qwen3.8-strix-optimizations, Dankclaw Improvements: TTM pages_limit now 114 GiB
(applied 2026-08-25), full 262k KV + Q8 payload fit in one slot
- frank_large_config.bats: assert 262144 context, reasoning + preserve_* enabled
The TTM/GTT was raised to 114 GiB (29,883,536 pages) to hold the full 262k KV.
Replace the retired kingjones ROCmFP4 STRIX MTP payload on Dankclaw with
cafonz/Qwen3.8-27B-ROCmI4-MTP-GGUF (eemin namespace, public), served by the
charlie12345/ROCmFPX llama.cpp build (ROCmI4 W4A4, c49ebdbd) on the Strix Halo
iGPU. Q4_0_ROCMI4 with an embedded NextN/MTP head (no separate draft file);
strict-Qwen MTP n16/p0.60/backend sampling on ROCm0. Binary
/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server; model dir
/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP. Updated serve script + env,
ubatch bench, large-config bats test, docs, AGENTS.md.
Operator request (2026-08-22): the primary inference server
(frank-default-large, the 27B CIRU model on Dankclaw) moves to the
standard llama.cpp port 7770. Both LLM services now listen on :7770,
distinguished by host (dankserver vs dankclaw).
Functional changes:
- scripts/frank-default-large.env: LISTEN_PORT 52625 -> 7770
- scripts/serve-frank-large.sh: default LISTEN_PORT 52625 -> 7770
- scripts/deploy.sh: LLM_HEALTH[dankclaw] -> :7770
- open-webui quadlet: OPENAI_API_BASE_URL -> 192.168.0.143:7770
(re-pointed so chat keeps working; data dir preserved)
- scripts/bench-fast-greedy.sh: PORT 52625 -> 7770
Tests updated to the new topology (both LLM endpoints on :7770 by host;
open-webui -> :7770). Docs + pi KB updated; dated historical runbooks
keep their point-in-time ports. models.json (pi client) re-pointed to
:7770 separately, effective on the next client restart.
One repo, one git protocol, one deploy script. Merged from the two
former AGENTS.md files:
- Overview: both workloads, both hosts, the 2026-08-22 merge note,
current LLM fleet topology (frank-default-small :7770 Dankserver,
frank-default-large :52625 Dankclaw)
- Git workflow + testing (serverAppConfigs protocol, test step kept)
- Deployment: the unified deploy.sh (stack + LLM per target)
- Secret rules: no passwords in the repo; FRANK_SUDO_PW covers
headless sudo (the live sudo password is NOT carried forward)
- Deletion & Trash Policy (from the vllmScripts 2026-08-22 commit)
- Benchmarking policy (stop the service before any bench)
- Pi model config, runtime & troubleshooting (v3 CIRU active,
Kairic/DFlash2/FastMTP retired), HIP env naming rule, crash-loop
procedure, operational quirks (passwordless sudo verified
2026-08-22), Dankclaw memory model
- README: fix broken 'Also See' placeholder URL -> live Gitea LAN URL
- index.md: expand vllmScripts See Also with the endpoints it serves
- OpenWebUI.md: :7770 backend is the llama.cpp PP head (split to the
3090), managed by vllmScripts; note the FLM NPU :52625 alternative;
fix the broken [[llama.cpp Server]] wikilink
- Gitea.md: hosted repositories table (both projects)
- Dankclaw Stack.md: host-level LLM endpoints in the service inventory
- AGENTS.md: runtime note — LLM endpoints live in vllmScripts, not here
Pre-existing failures (untracked ComfyUI WIP): tests 6, 8, 9, 10.
Docs seams green: ok 19 (compose service docs), ok 20 (index links).
Frank