Both rungs now sit on the same unwrapped corpus with seed, steps and token count
held, so carrier size is the only difference and the effect is attributable:
held-out 3.329 at 0.6B against 3.018 at 1.7B, a gap of 0.311 nats. The chained
0.6B rerun closed the confound the unwrap opened.
Two things in those numbers need stating or they will be misread.
First, the original wrapped-corpus 0.6B reached 3.172, which looks better than the
unwrapped 0.6B's 3.329 and is not. Different corpus means a different held-out
set, and the wrapped version's 5.7% newline tokens are near-deterministic after a
70-character line, so they deflate the loss with cheap wins. Removing them removed
the easy tokens. It is a measurement artifact, not a regression.
Second, a correction to my own earlier claim: I twice described the 0.6B run as
still descending and undertrained at 3.172. Its series reads 3.176, 3.173, 3.172,
3.172 -- it flattened. All three runs plateau, so one epoch is about right for
this corpus rather than short.
The three-way booth puts 1.7B base, 1.7B tuned and 0.6B tuned side by side on the
same nine prompts and seeds. The base arm is the control that matters: curly
quotes go 0 of 18 on 1.7B base to 15 of 18 on 1.7B tuned, and worksheet-or-
explainer collapse goes 3 of 18 to 0 of 18, so the shift is the adapter rather
than the larger carrier. Hard-wrapping fell from 0.85 to 0.18, confirming the
corpus unwrap carried through into the adapter.
Sense partially returned. The 1.7B arm produces locally coherent sequential
Victorian prose where the 0.6B produced word salad, but scene-level continuity
still breaks mid-passage.
One observation held loosely: curly quotes are slightly lower at 1.7B than 0.6B,
which would fit a bigger model's stronger priors resisting the adapter at the same
rank. That is untested and is not offered as established.
Operator: "loading up the context killed sec again." That reproducer is what
finally made the failure legible, and it showed the previous four fixes had all
been aimed at the wrong quantity.
What the KV pool can hold and what the card can process at depth are different
numbers. Cutting context 420k to 384k to 320k, pinning the KV in bytes, and
dropping the prefill chunk from 16384 to 4096 all sized the pool. The crashes were
governed by the transient needed to process a prefill chunk against a quarter
million tokens of resident KV, which scales with depth and not with pool size.
Each change helped and none fixed it.
Bisected against the real reproducer, with a non-repeating prompt because prefix
caching would let a repeated one hash to cached blocks and never prefill deep:
113,247 prompt tokens SURVIVED (27 s)
200,088 prompt tokens SURVIVED (174 s)
~285,000 prompt tokens ENGINE DIED, HTTP 500, container restarted
The sustainable ceiling therefore sits between 200k and 285k with gen idle, and
gen shares the card with its load uncontrolled, so 163,840 takes about 20% margin
under the proven-good depth rather than sitting at the measured edge.
The ceiling's purpose is the refusal. Verified after the change: a 149,073-token
request serves in 41 s, and requests at both 200k and the ~285k depth that killed
the engine now return a clean 400 naming the limit in under a second with the seat
untouched. A seat that refuses what it cannot serve is strictly better than one
that dies trying.
Concurrency went 1.03x to 2.09x. The compose header's "served at native 262K" was
never actually deliverable on a shared card; it had simply not been exercised at
depth until today.
The probe is committed rather than described, so the ceiling can be re-measured
when the card's tenancy changes.
Operator: "start the 1.7b training."
The 0.6B adapter learned the Gutenberg transcription's ~70-character line breaks
along with the prose -- its output wrapped at a mid-length-line ratio of 0.85
against the base model's 0.00. That is typography rather than style, and every
further rung would have inherited it, so the corpus is reflowed before rung 2
rather than after the sweep.
The reflow joins 57,430 of 85,380 paragraph blocks and keeps 27,950. Verse is the
hazard a blind join would destroy, so the decision is per block by median line
length: blocks whose lines cluster near the wrap width are flowed prose, blocks of
consistently short lines keep their breaks. Every kept multi-line block in the
sample was genuinely verse with its lineation intact. No line ended in a lone
hyphen, so the space-join could not split a word across lines. The acceptance
check is content identity -- " ".join(text.split()) byte-identical before and
after -- and it passed on all 852 records, proving only whitespace changed.
Concrete cost of the old defect: 5.7% of the training budget was newline tokens.
The same words pack to 5,210,112 tokens unwrapped against 5,525,504 wrapped.
The 1.7B run is live at 159 steps and roughly 18.7 s/it. Everything but the
carrier and the corpus is held from the 0.6B run: seed 4919, rank 32, lr 1e-4, seq
4096, batch 1 by accum 8, one epoch, eval and save every 25 steps so the minimum
is located rather than assumed.
That corpus change is a second variable and it is named as one. A 0.6B-vs-1.7B
comparison is descriptive, not attributable, until the chained 0.6B rerun on the
same unwrapped corpus lands behind it -- gated on the 1.7B actually producing an
adapter, because a chain that fires on failure turns one lost run into two.
"Did sense come back at 1.7B" is a within-arm reading and survives the confound;
any between-rung delta does not.
The original wrapped corpus is untouched, so the 0.6B run's pinned corpus sha
3959036cf851bf62 stays reproducible.
Operator: "yes, pin the kv and take it to 320k."
The real finding, which took three crashes and two failed attempts to reach:
--gpu-memory-utilization does not bound actual usage. It sizes the KV
calculation, but peak activation is measured at profiling time and real
long-context work exceeds the profile. vLLM's own budget line showed mog-sec
running 0.9 GiB over its 47.48 GiB reservation -- 26.44 consumed plus 3.53 peak
activation plus 0.89 CUDAGraph plus 17.52 KV equals 48.38 -- and gen was over by
0.33 on the same card. That overage came out of the shared card's slack, which is
what kept OOMing after the utilization drop.
The fix is the one vLLM printed itself: --kv-cache-memory=17697765376, its own
recommended figure to fit inside the requested budget. Same discipline erp-seat
already uses, and for the same stated reason -- an explicit figure is
reproducible where a ratio silently yields a different cache depending on what
else is resident at start time.
The KV pin and the context length are coupled. 16.48 GiB yields about 383,730
tokens, so a 393,216 max_model_len falls under the 1.0x floor and vLLM refuses to
start rather than crashing later; pinning the KV while keeping 384k was never an
available combination. 327,680 leaves 1.15x, up from 1.03x.
Verified: the engine now logs "reserved 16.48 GiB memory for KV Cache as
specified by kv_cache_memory_bytes config and skipped memory profiling", KV
375,901 tokens, GPU0 down to 90,561 MiB from 91,313, RestartCount 0, and both sec
and sec-reasoning return 200 through the gateway.
Also records the BabyBronte eyeball A/B, whose result is the operator's own: the
voice transferred and the sense did not. Curly quotes went 1 of 18 to 18 of 18
and worksheet collapse 3 of 18 to 0 of 18 between arms. That voice is separable
from coherence at 0.6B is the premise the lightweight-adapter regime rests on, so
this is the informative outcome rather than a disappointing one. A corpus-prep
defect surfaced with it: the tuned output is hard-wrapped at about 70 characters
because the Gutenberg source kept its line breaks and the adapter learned the
typography too.
Cost: 320k of context instead of 420k, on a seat whose crashes happened at 151k.
sec/sec-reasoning crash-bounced twice in ten minutes, not once in thirteen days.
My earlier read of "rare, not chronic" came off a RestartCount of 1 and was
wrong; the operator pushed back and the second and third failures arrived while
that recommendation was still on screen. The memory entry making that call is
replaced rather than left standing.
Cause is unchanged from the first diagnosis: mog-sec at 0.52 plus gen at 0.38
reserve 0.90 of the card, leaving about 4.6 GiB, and vLLM's utilization figure
covers weights and the KV pool but not transient activation memory. A request
about 151,700 tokens deep scheduling a further 15,700-token chunk asked for 1.04
GiB with roughly 600 MB free.
Dropping utilization alone does not work, and fails in a worse way: a single
420,000-token sequence needs 17.88 GiB of KV, and at 0.50 the pool is 17.4 to
17.5 GiB, so vLLM refuses to start at all and the seat crash-loops during startup
instead of during a request. The context length and the crash were directly
coupled -- 420k was only reachable at the utilization that left no transient
headroom. So both moved: 0.50 and 393,216.
384k rather than vLLM's suggested maximum, deliberately. It estimated 406,352 on
one boot and 409,840 on the next, because the available-KV figure drifts about
0.1 GiB boot to boot; pinning the edge value fails to start on an unlucky boot.
393,216 sits 3% under the lower estimate and leaves roughly 0.7 GiB of the pool
unspent, which is the transient headroom the change exists to buy.
Verified after: KV 405,612 tokens, concurrency 1.03x at 393,216, and both sec and
sec-reasoning return 200 through the gateway.
num_speculative_tokens is documented as NOT the lever. The crash window logged
17.6% draft acceptance with positions 5 through 7 at 1.5 to 4.9 percent, which
reads as an obvious cut from 7 to 3; across 180 samples the median acceptance
length is 3.12 of 7 and median draft acceptance is 30.4%, so the crash window sat
near the minimum and cutting would cap the workloads accepting nearly the full
draft.
Cost: 384k of context instead of 420k, an 8.5% reduction on a seat whose crashes
were happening at 151k.
sec/sec-reasoning on ana-ml2 :8019 took a CUDA OOM on GPU0 at 13:20 PT and
auto-recovered in three seconds. First fatal error since the container was
created on 2026-08-28. A request already 151,728 tokens deep scheduled a further
15,696-token chunk, needed a 1.04 GB allocation, and found about 600 MB free.
EngineCore died, the API server exited 0, and restart: unless-stopped brought it
back; the dockerd journal records manualRestart=false, so nothing restarted it by
hand.
Not caused by the same-day char-rp-fast swap. That work was entirely on GPU1 --
erp-seat is pinned device_ids ["1"] -- and GPU0 read 93,257 MiB both before it
started and after it finished.
The standing condition is that GPU0's two seats reserve 0.38 plus 0.52 of the
card between them, leaving about 4.6 GiB, and vLLM's utilization figure covers
weights and the KV pool but not all transient activation memory. Long-context
prefill chunks with speculative decoding live in what is left.
Also recorded as a specimen: the crash window logged a 17.6% draft acceptance
rate with positions 5 through 7 accepting 1.5 to 4.9 percent, which reads as an
obvious case for cutting num_speculative_tokens from 7 to 3. Across 180 samples
of the same counter the median acceptance length is 3.12 of 7 (range 1.83 to
6.75) and the median draft acceptance is 30.4% (range 11.9 to 82.1). The crash
window sat near the minimum. The single window pointed the opposite way from the
distribution, and acting on it would have capped the workloads that were
accepting nearly the full draft.
No configuration changed. One self-healing failure in thirteen days does not
justify shrinking a KV pool on a seat configured for 420k context.
Operator: "replace that a4b moe over pfish-6 -- remove the pfish-6 alias and
create an alias for char-rp-fast."
G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16 is live on ana-ml2 :8021 under
its own served name, behind the new gateway alias char-rp-fast. Pfish-6 is gone
from the gateway and now returns an explicit 400 rather than a substitution; 0 of
17 LiteLLM keys scoped it, so nothing was orphaned. The compose project name stays
erp-seat because asset-engine derives seat liveness from it.
The first quant of that A4B served NaN and passed its healthcheck doing it. It was
built with the dense v2-31B recipe, whose ignore list has no router regex, so all
30 MoE routers were quantized to 4 bits -- and a 4-bit router changes which experts
run rather than degrading them. Quant rc=0, healthcheck green, correct KV pool,
correct served name, and every completion returned finish_reason=length with the
full token count and content: null. The model was emitting a full budget of tokens
that decoded to the empty string. Raw /v1/completions was empty too, ruling out the
chat template and the reasoning parser. The signal that named it was logprobs:
vLLM refused to serialize the response, "Out of range float values are not JSON
compliant: nan".
The lesson is about the control rather than the router. That tree had already been
structurally diffed and passed -- against a verified-good DENSE quant of the same
Gemma-4 family. A dense model has no routers, so the single thing that was wrong
was the single thing the control could not distinguish. Diffing instead against
Pfish-6, a known-good quant of the same 26B-A4B MoE, gave it in one line: 222
ignore entries against 252, the 30 missing being layers.N.router.proj. A positive
control is only worth what it can distinguish, and "same family" is not "same
architecture class".
Re-quantized with the MoE recipe, whose dry-run asserts 11,520 expert Linears and
refuses a router in the quantize set before any GPU time. The live seat then passed
prose with no channel-prefix leak, a solid-colour image read correctly, an auto
tool call parsed, finite logprobs, and KV 534,649 tokens / 2.04x carried over from
Pfish-6 unchanged. The broken tree is parked on ana-ml2 as
...-NVFP4A16.BROKEN-routers-quantized-20260910.
Section 4.4's temp port was not reachable: 15.9 GiB of weights plus KV plus
multimodal encoder-cache profiling does not fit in the ~19 GiB free beside GPU1's
six other tenants -- 0.20 utilization refused admission, 0.185 OOM'd in encoder
profiling. The substitute was reversibility and ordering: named .env backup, prove
the seat on its real port while no alias points at it, move the alias last. That is
why a NaN-serving seat never reached a consumer. The seat was down about 16 minutes
across two attempts; no consumer saw a broken alias.
Playbook gains the router-quant failure signature and the control-class rule in
3.15, and a logprobs check in 4.4. seat_verify.py carries that check as check 6.
Quality is NOT established: no RP eval, no long-context check, no A/B against
Pfish-6 or char-rp. Samplers are the author's card values, untuned here.
The v2 dense quant had failed four times. Attempt 5 lands it at 19 G.
The blocker was not what it looked like. `AmbiguousGlobalPerLayerAttributeError`
on `head_dim` read as a malformed upload -- DogOnKeyboard's config carries a
`per_layer_config` key zerofata's canonical one lacks -- and the standing fix was
to force `allow_global_per_layer_attribute_access=True`. Both halves were wrong.
`pip install llmcompressor==0.13.0` downgrades transformers 5.16.1 -> 5.14.1. The
config was serialized by 5.16.1, which materializes `per_layer_config` from
`global_head_dim` + `layer_types`; 5.14.1 carries the heterogeneity guard but not
the gemma4 resolver. Under the image's own transformers the same config loads
fine. `:latest` was also re-pulled during attempt 4 and no earlier run, so the
toolchain moved mid-diagnosis. Two things separated "malformed upload" from
"moved toolchain": reproducing the real failing call (a bare AutoConfig load does
not reproduce it; the trigger is reached through AutoTokenizer) and keeping
zerofata's canonical tree, quantized cleanly on 2026-08-21, as a positive control.
The fix drops `per_layer_config` rather than forcing global access. It is exactly
redundant -- keys are precisely the ten full_attention layer indices, sole value
(512, 4), verbatim the global fields -- and forcing instead would make
`config.head_dim` answer 256 to the callers building the 512-wide layers.
patch_perlayer.py re-proves that redundancy at apply time and refuses if it ever
stops holding.
Verified on the tensor table rather than the exit code: the output is identical
family-for-family and count-for-count to the August canonical quant, with 356
BF16 vision-tower tensors preserved and input_activations=None. A GPU-free load
leaves 0 tensors on meta and generates coherent prose. The section 4.4 serve test
has NOT run -- GPU1 has 19.9 GB free against 19.5 GB of weights, so it needs a
live seat displaced.
Also fixes the A4B output, which had a truncation cap baked into its tokenizer
(max_length 8192) from being quantized with the calibration corpus.
Playbook gains section 3.17 for the pinned-transformers class and sharpens 3.16
to say drop the dataset outright for any A16 scheme.
Ships the two pending code changes alongside the memory that describes them:
train_voice_lora.py gains --eval-steps/--save-steps (the 3-epoch pilot overfit
with per-epoch eval and save_strategy="no", so the minimum was neither visible
nor recoverable), and the althing post-office compose is pinned to 3.6.2.
Index rewritten: in-flight compressed from 176 lines to the live state, three
detail files added for R49 D1-D3, the MeroMero four-failure chain, and the
althing rollout. Seven closed pre-08-27 entries archived; the guards held back
the rest because they carry open deferred pointers.
The LossLog callback filtered on `"loss" in logs`. Trainer emits eval under
`eval_loss` with no `loss` key, so every eval record was discarded and
loss-series.json showed zero eval points while the log a metre away carried
`eval_loss: 3.198`. An artefact that omits data which demonstrably exists reads as
"no eval was run" rather than "the collector dropped it", which is the failure mode
that costs someone a re-run.
Collector now accepts either key. Seed 2 gets it from launch; seed 1 is already
running with the old code, so recover_eval_series.py parses the eval records back
out of its log -- the data was printed, not lost -- and the chain runs that
recovery before cutting the generation arms, so the artefact is complete before
anything reads it.
The two seeds therefore differ in logging code but not in training math: the
callback only affects what is recorded, never what is computed, so the weight
trajectories remain comparable. Noting it because a difference between the two
arms whose spread sets the decision threshold is worth stating even when it is
provably inert.
brokkr-smithy corrected H02's incumbent naming: qwen3.6-35-a3b-heretic was retired
from the gateway roster on 2026-08-15 and is not what Skaldsong would call today.
Verified against the gateway and the seat itself -- alias `gen` resolves to
hosted_vllm/qwen3.8-27b-uncensored on ana-ml2:8015, container vllm-gen, 262,144
ctx. The arm targets that.
24 records, style-prompted on the same prompts and sampler as the other arms.
Alias resolved at run start AND end and confirmed stable across the run, per the
fleet rule that an artefact records the backing model rather than the alias.
Two things recorded rather than glossed:
The harness is NOT matched to the other arms and the artefact says so. Base and
adapted arms are local transformers on gx10; the incumbent is a served NVFP4 27B
reached over the gateway, and it is an instruct model receiving a style
instruction where the others are base models receiving none. That asymmetry is the
comparison H02 asks for -- prompted imitation against trained voice -- but it must
not be reported as if the harnesses were identical.
The gateway echoes the ALIAS in each response's `model` field, so a row read on
its own would have recorded "gen" as provenance -- the same class of mistake that
inflated an exposure count 4.7x on this fleet. Rows now carry
alias_echoed_by_gateway beside backing_model_resolved and its date, and the
generator was fixed at source rather than only in the emitted file.
Sanity: median 392 completion tokens, zero records opening with markdown or
meta-commentary, output reads as continuation prose. The style prompt was written
to be a fair incumbent rather than a strawman, since this arm is what the adapter
must beat.
Entity resolution, deterministic rename augmentation, packing and the pilot
trainer. Qwen3-0.6B-Base is training now: 507 steps, 11.2 s/it, ~1h35m.
D2 -- gender resolution is TITLE-FIRST, and that is a change from F02's method
rather than a port of it. F02 used pronoun proximity and recorded that it is
structurally blind to the first-person narrator, whose name appears mainly in
dialogue surrounded by other people's pronouns. Measured here, proximity called
JANE MALE -- the narrator of Jane Eyre and the single worst entity to get wrong.
Titles have no such blind spot: Miss Eyre, Mrs. Fairfax, Mr. Rochester, Madame
Beck, M. Paul, and a 19th-century novel is saturated with them. Measured: 16
entities resolved, zero wrong, every ambiguous case landing on HELD -- shared
family surnames like Helstone and Pelet genuinely belong to both a man and a
woman and hold as they should.
Held means ungendered, not unrenamed. A HELD entity is still renamed, from the
gender-neutral surname pool, because the operator's Yarros directive was "rename
all proper nouns" and holding a place leaks it -- Thornfield appears 100 times in
Jane Eyre and is as author-specific as Riders Quadrant was. Substituting a neutral
token makes no gender claim, so no gender claim can be wrong.
D3 -- pool is French + English per the operator, weighted per work by setting:
Brussels novels 60% French, Yorkshire novels 25%. Locales restricted to
fr_FR/fr_BE/en_GB/en_IE; en_US and en_AU carry modern surnames that are wrong
register for the 1840s. The pool is filtered against Brontë's own 75-letter
alphabet, so French accents stay and Czech/Latvian marks do not.
Two collision defects found by running the leak gate rather than trusting it:
`Burns` and `Marie` were drawn as replacements while being Brontë characters --
F02's collision filter was built against Yarros and does not carry -- and then
`Pierre-Yves` passed a whole-string filter while `Pierre` (Mademoiselle St.
Pierre) is a Villette character. The filter now compares by COMPONENT. Final gate:
0 of 203 source entities survive in any of 24 copy-files.
Trainer records what the run RESOLVED to rather than what it requested -- attention
implementation, dtype, device, corpus sha and harness cleanliness are read back off
the live objects. transformers 5.x has dropped warmup_ratio, caught by reading the
signature after the first launch failed on it; the 3% warmup is computed into
warmup_steps instead.
scripts/r49-corpus/{build_corpus,verify_corpus}.py; corpus staged at
gx10:~/r49-corpus/. Catalogue ids verified against gutenberg.org's own search
rather than recalled. Charlotte only -- the Bell poems are co-authored and the
Gaskell biography is a different hand, so neither belongs in a single-voice corpus.
Jane Eyre 1260 · Villette 9182 · Shirley 30486 · The Professor 1028
680,291 words · 142 chapters · 950,974 Qwen3 tokens (1.40 tok/word)
alphabet 75 letters, 23 non-ASCII · round-trip lossless · 0 byte-fallback
All 11 acceptance checks pass, including both tokenizer legs run against the pilot
carrier itself. With a real denominator the projections tighten: at 6 rename copies
x 3 epochs = 17.1M tokens, the 0.6B pilot is 1.98 h.
THE ALPHABET INVERTS THE YARROS RESULT. Brontë writes French constantly -- Villette
is set in a French-speaking city, Jane Eyre has Adèle, The Professor is set in
Brussels -- so the corpus carries é 432, è 237, à 93, ê 79, ô 48 plus œ and æ. F02
measured Yarros at 0.0002% non-ASCII and derived an ASCII-fold for the name pool.
Under F02's own subset rule the Brontë pool may keep FRENCH accents and must still
exclude the Czech/Latvian/Slovak/Hungarian marks that never appear here. The fold is
per-work, and this is the first corpus where deriving it changes the answer.
Typography was inconsistent across works and it was the transcriber, not the author:
Shirley uses straight quotes and `--` with zero em-dashes while Jane Eyre and
Villette use curly and em-dash. Normalised toward what the text means.
Three defects, each found by running something rather than reasoning about it:
`Produced by` matched Brontë's own prose four times, which is the adjective-"minor"
shape again and is fixed by anchoring boilerplate patterns to line start; asserting
open/close quote counts must be equal is wrong, because 19th-century multi-paragraph
speech legitimately runs a surplus of opens, so the real error signature is that no
paragraph may begin with a closing quote; and The Professor's table of contents puts
two chapter names per line, so a bare regex returns 38 headings for a 25-chapter
novel and a minimum-gap filter still leaks its tail -- the rule that works is that
the body's "CHAPTER I" is the last one in the file.
Records the operator's pilot ruling: trial on Qwen3-0.6B-Base first, move up only if
it produces something useful.
CronList showed job 12bdea3c firing hourly at :37 with the verbatim "check on the
run ... inform brokkr when ready" text; CronDelete removed it and the list is now
empty. No crontab entry, user systemd timer, or background shell was re-seeding
it -- the only on-disk hits are conversation transcripts.
This is at least the second kill: the operator killed the same loop on 09-09
("kill the check, no training is running") and that session's handoff warned
against starting one. The warning was insufficient because a cron-fired prompt
arrives as an ordinary user turn with no marker, so it is indistinguishable from
the operator typing it -- three turns went into re-verifying an idle fleet and
answering a timer carefully.
The memory entry now says what to DO rather than what not to start: run CronList
before answering that prompt, and treat a second identical arrival as a signal to
check the cron list rather than answer again. Worth the prominence because the
instruction chain ends in three outward-facing acts -- an althing message to
Miranda, standing up a serving seat, and cueing brokkr -- every one of which
carries something false when no run exists.
uv tool install --force --reinstall from ~/development/althing (clean tree, HEAD
== origin/master 719bc5f, pyproject declaring 3.6.1). althing-core 3.6.0 -> 3.6.1;
herald PID 2457743 -> 3690918 with the old process confirmed gone; version read
back from the running install; postbox status reachable/push/alive; journal clean
since restart. postbox, althing-listen and althing-route moved on the same install.
Six boxes stay queued and the plugin hop (0.1.6) is separate and not done, so this
is deliberately not a "fleet done" claim. Reported to forseti per box.
Records one verification trap worth keeping: POKE_TEXT in post_office_herald.py is
a four-part implicit string concatenation, so a line-oriented grep for the new poke
sentence returns empty on a CORRECT 3.6.1 checkout. The first pass came back empty
for both the new text and the old, which reads as "new absent, old removed" -- two
wrong conclusions from one wrong pattern, detectable only because both cannot be
true at once. Check the effective value: reconstruct the concatenation or import
the module and print the constant.
Operator: "purge the merged models, keep run06 and the v6 quant." Eleven merges
removed with literal paths, one rm per line.
pfi-gx10 merged-run03c, merged-run04, merged-run05 3 x 49 GiB -> 145 GB
ana-ml2 merged-final, merged-run02, merged-run03,
merged-run03-s{025,050,075}, merged-test,
nvfp4a16-test 8 dirs -> 354 GB
gx10 382G->237G used, 632 GB free. /tank/erp-tune/serve 354G->8.6M with no
snapshots holding the blocks; the pool's raw FREE moved 4.80T->5.30T. Combined
with the earlier checkpoint purge, ~573 GB reclaimed tonight.
The check that made this safe: docker inspect on the live vllm-erp-seat shows it
binds /tank/aimodels ONLY, with model arg /tank/aimodels/erp-tune-v6-nvfp4a16, so
/tank/erp-tune/serve was never in the serving path. Also confirmed no container
mounts that tree and no process held a file open under it, reading /proc/*/fd and
/proc/*/maps rather than trusting an empty lsof. All eleven were run-1/2/3-era
Gemma-4 merges dated Aug 24-26; the keeper is dated Sep 8 and lives in a different
tree, so there was no ambiguity about which was which.
Kept and re-verified after the deletion: gx10 serve/merged-run06,
/tank/aimodels/erp-tune-v6-{bf16,nvfp4a16}, all eight adapters sha256-unchanged,
and the merge/quant tooling and logs under /tank/erp-tune/serve (8.6 MB) that
document how the artifacts were built.
The live seat never bounced -- Pfish-6 answered a real completion after the delete
with finish_reason stop and correct text, container still healthy at 4 h uptime.
relaunch-trial-seat.sh now names a deleted model; it was banner-marked RETIRED
rather than removed, because its flags carry the FlashInfer JIT/PATH trap and the
gpu-clear / never-pkill notes.
The operator asked brokkr-smithy to look for a smaller Qwen3.6/3.8; brokkr reported
none exists and that both 27Bs are the same hybrid kernel path one size up. Verified
independently against the HF API rather than adopted, and it holds -- with two facts
brokkr's note did not carry.
1. No official Qwen3.6 or Qwen3.8 below 27B. The listing is Qwen3.6-{27B, 35B-A3B}
and Qwen3.8-{27B, 2.4T-A95B, Flash-Next}.
2. Neither family publishes a -Base checkpoint AT ALL. Every Base newer than Qwen3
is Qwen3.5. Since the regime requires a non-instruct carrier, that rules the
3.6/3.8 lines out on its own, independent of size.
3. Qwen3.6-27B and Qwen3.8-27B both report model_type qwen3_5, 64 layers as 16 full
+ 48 linear-attention, vision tower present -- confirmed as stated.
So the dense Qwen3 ruling is not a compromise against a better available option; it
is the only dense Base option. Also recorded as insurance, not a proposal:
Qwen3-8B-Base and Qwen3-14B-Base exist, so the sweep can extend past 4B without
changing family if the carrier curve has not flattened there.
brokkr-smithy flagged that R49 F02's name-pool token splits were measured with the
Qwen3.5-2B tokenizer, so the dense-Qwen3 carrier ruling invalidates them. Measured
rather than left on their critical path; handed over as input to their re-check,
since the dictionary and the adjudication are theirs.
The multi-token property strengthens on the chosen carrier: pool multi-token
88.0% -> 90.3%, mean tokens 2.33 -> 2.46. A smaller vocabulary fragments more, so
Qwen3's 151,936 splits names into more pieces than Qwen3.5's 248,320. The operator's
requirement that names be multi-token, so the drafter reconstructs them from the
prefix instead of recalling one embedding, is better served after the ruling.
Positive control: the Qwen3.5 column reproduces F02's published figure on the same
pool and tokenizer (F02 89% / mean 2.35; here 88.0% / 2.33), so the instrument
recovers a known-true value before being asked about an unknown one. The pool is
deduped across locales, which reconciles male_given and female_given exactly
against the dictionary's own totals block.
Two operator rulings, 2026-09-09.
"purge intermediate checkpoints" -- seven checkpoints/ directories removed with
literal paths, one rm per line, after confirming none was a symlink and that
every run's final adapter/ is an independent real directory:
pfi-gx10 run-03c 11G run-04 16G run-05 9.2G run-06 9.2G = 45 GB
ana-ml2 run-01 12G run-02 12G run-03 5.9G = 29 GB
gx10 419G->374G used, 496 GB free. /tank/erp-tune 392G->363G with zfs list -t
snapshot empty, so the space is genuinely returned rather than snapshot-held. All
eight adapters re-verified by sha256 after the deletion, matching the values
recorded during the mirror. Merged artifacts deliberately untouched -- they are
not checkpoints, and the ~550 GB of superseded merges stays a separate call.
"use dense qwen3" -- the R49 H02 carrier sweep becomes Qwen3-{0.6,1.7,4}B-Base,
which overrides the Qwen3.5 arms H02 names; brokkr-smithy owns that file and was
told directly. Qwen3-4B-Base staged and benched to complete the family:
Qwen3-0.6B-Base 0.616 B 1.707 s/step 2,399 tok/s spread 0.6%
Qwen3-1.7B-Base 1.755 B 2.895 s/step 1,415 tok/s spread 0.8%
Qwen3-4B-Base 4.089 B 5.714 s/step 717 tok/s spread 0.3%
The dense 4.089 B carrier still trains 33% faster than the hybrid 0.765 B one.
Projected per voice 2.7 / 4.6 / 9.1 h; the three-arm sweep at two seeds is ~33 h
of GPU, ~10 h if H03's corpus floor holds. The three Qwen3.5 checkpoints stay
staged so the decision is reversible behind an fla install.
Also recorded: verified at 22:45-22:48 PT that nothing is training on gx10,
ana-ml2, nh3-dev or irv-ml1, and that brokkr's own run07-gate close states
"Nothing is owed. No battery to run." Run 7 has no servable artifact left. And a
correction to a standing lesson -- the bracketed-class trick does not defeat a
wrapper's argv, since the invoking shell's command line carries the literal
pattern; observe the artifact instead.
The base-viability pre-flight had three checks (fits / MoE expert mapping / LoRA
support) and would have passed Qwen3.5-0.8B-Base clean while it trained 2.6x
slower than a dense model 2.3x its size. Check 4 closes that: read `layer_types`
for a linear_attention majority AND probe for mamba_ssm / causal_conv1d / fla /
kernels. It is the intersection that is slow -- a hybrid shape with the kernel
present is fine, a dense shape does not care.
Carries the measured table (gx10 GB10, n=10/arm, spreads 0.6-2.6%), plus the two
things a hybrid Base checkpoint brings that a dense one does not: a vision tower
and MTP head that target_modules="all-linear" would train on text, and the module
rename that AutoModelForCausalLM introduces relative to the vLLM serving class;
and unsafe cross-document packing, since SSM state ignores the attention mask.
Section heading corrected from "three greps" to "four checks". The example was
made runnable and verified on the box rather than shipped untested.
Prep for the BabyBronte / brokkr-smithy R49 author-voice adapter regime, plus
the operator's "keep the adapter" ruling made durable.
Measured on pfi-gx10 (GB10, sm_121), n=10 per arm after 3 warmup steps, seq
4096, LoRA r=32 on q/k/v/o + MLP, bf16, sdpa, grad-checkpointing on:
Qwen3-0.6B-Base dense 0.616 B 1.707 s/step 2,399 tok/s
Qwen3-1.7B-Base dense 1.755 B 2.895 s/step 1,415 tok/s
Qwen3.5-0.8B-Base hybrid 0.765 B 7.581 s/step 540 tok/s
The dense 1.755 B carrier trains 2.6x faster than the hybrid 0.765 B one on 2.3x
the parameters (~6x per parameter), with more LoRA modules adapted (196 vs 96).
Spreads of 0.6-2.6% put instrument noise an order of magnitude below the effect.
Cause: Qwen3.5 is 18 linear-attention (SSM) layers to 6 attention, and no fused
linear-attention kernel is installed on the box. Grad checkpointing is not the
culprit (19%, and saves 2.6x memory). Batching is not the lever for either
family -- both sit at this box's roofline at batch 1.
Projected per voice on a Brontë-scale corpus: dense 0.6B 2.7 h, dense 1.7B
4.6 h, hybrid 0.8B 12 h. The hybrid would take longer than the 7 h 26B-A4B tune
the regime exists to replace, so the carrier family is now an open decision with
a recommendation for the dense Qwen3 line -- the design doc's original pin.
Two further Qwen3.5 findings, both measured rather than read off the config: the
Base checkpoints ship a vision tower (153/297 model.visual.* Linear tensors that
target_modules="all-linear" would train on text) and an MTP head, both dropped
for free by loading through AutoModelForCausalLM -- which renames modules
relative to the vLLM serving path, so adapter binding needs the
sampled-target-changed check on the serving side; and cross-document packing is
unsafe because SSM state ignores the attention mask, breaking the per-copy
name-consistency invariant the design doc calls sacred. Neither exists on dense.
Adapter disposition, per the operator's ruling: all five gx10-resident ERP
adapters (run-03c/04/05/06/07) mirrored to ana-ml2:/tank/erp-tune/run-<N>/adapter
matching the layout runs 01-03 already used, byte-totals identical both sides and
sha256 matching on every adapter_model.safetensors. /tank/* is deliberately
excluded from ana-ml2's restic sources, so the profile gains one documented
carve-out for /tank/erp-tune/run-*/adapter, verified by resticprofile --dry-run
to expand to exactly those eight paths.
Nothing is training and nothing is queued.
Operator ruling: run 6 is declared Pfish-6 and is the standing seat; run 7 is
retired (its gate failure was the detector bug fixed in cc42d76, but the run was
independently poor).
- served under its TRUE name Pfish-6; LiteLLM alias trial -> Pfish-6
- ana-ml2 :8021 and pfi-gx10 :8098, both at 262,144 ctx, same artifact
- SPEED: moe_backend=flashinfer_cutedsl PROVEN unusable here (engine init fails,
'kernel does not support current device'); Marlin is correct for a weight-only
scheme, and vLLM's 'no native FP4' warning is about the scheme not the card
- the real lever was max-num-seqs 8 -> 32: n=8 1269 tok/s and n=16 2170 tok/s,
3.2x the old ceiling, with single-stream latency unchanged
- head-to-head measured: ana-ml2 is 4.1x FASTER than the GX10, not slower
Quantifying exposure to a gate-failed tune: counting by the gateway alias gave 363
rows, counting by the artifact gave 77, because the alias had carried three
different models that day. Wrong in the direction that looks careful.
From a near-miss brokkr-smithy-dev caught and declined to send: a post-fix
verification read raced a gateway restart and reported the alias still present.
A disagreement between two observers is not a finding until the boring
explanation is ruled out, and during an incident the pressure runs the other way.
Alias-present-with-backend-down is a different and worse state than
alias-removed: it re-arms silently the moment anything is served on
10.250.50.54:8021 again, and the next thing served there inherits a
fleet-reachable name without anyone deciding it should. Flagged by
brokkr-smithy-dev; same writer/reader-contract family as ops-lessons §11.
Commented rather than deleted so restoring is uncommenting, not reconstructing.
Verified: /v1/models returns 33 entries, trial absent, a caller gets a clean
400 'Invalid model name' instead of a connection error to a port that could
re-arm. Disposition of the artifact and the alias is the operator's.
- gx10:8098 erp-tune-v7 stopped 17:42; ana-ml2:8021 trial NVFP4 seat stopped 17:43
(infra-ops' call — the same adapter was on the SHARED-KEY gateway ~15:30-17:43
under the operator's pre-gate instruction; surfaced to him as reversible)
- probe NOT re-run, flagged generations NOT opened, length verdict left UNSET
- every artifact preserved; disposition is the operator's
- non-safety results recorded but explicitly NOT certified (primary flat +2,
diversity reduced, coherence 1.0 -> 0.875, control valid at 1.0)
The empty-snapshot promote and brokkr-smithy-dev's -s-on-a-touched-sentinel are
the same defect from opposite sides. Records the direction split (false
reassurance / false refusal / false alarm) because the mitigations differ and a
post-mortem that lumps them loses the actionable half.
ssh exiting 0 is not proof the capture is usable — the inspect script can emit
nothing and both refresh scripts would mv that over a good system-details.txt and
report 'ok (0 bytes)'. Every reader tests the snapshot with -s, so the writer was
producing an artifact its own readers call invalid: a guard whose test disagrees
with its writer's contract has quietly stopped guarding. Prompted by
brokkr-smithy-dev hitting the same shape from the other side (a -s test against a
sentinel written with touch, a precondition that could never pass).
- empty capture -> refused, previous snapshot kept, host counted as failed (exit 1)
- capture under 1/4 of the previous -> promoted but flagged, since a host can
legitimately shed services and the script should not guess
- header + CLAUDE.md contract lines corrected to say what is actually guaranteed
- verified red (empty inspect -> FAIL, snapshot intact, rc=1) then green (real host
-> ok 6727 bytes)
Operator: the form failed when a question was left blank. Refusing the whole
submission over one blank threw away the picks that were made, and the HTML
`required` on the radios blocked it in the browser before the server saw it.
- answered questions recorded; blank ones land in `unanswered`; `complete` says
whether the set is finished; a blank question carrying a note keeps the note
- `required` dropped from both templates so the browser cannot block a partial
- refused only when there is no pick anywhere AND no notes (a 400 — that would
flip an open ask to answered with no decision recorded); a choice outside the
option list is still an error
- new ◐ partial state with an n/N count; skipped questions render as skipped
- README + global CLAUDE.md tell reading sessions to check `complete`
- 154 tests; v0.1.15
Operator verdict on the separate /asks page: the question belongs with the
artifact it is about. A four-voice audition wants each voice's radio group
under that voice's audio, and one submit for the lot.
- booth/inline.py: data-booth-ask="stem" | "stem:key" | data-booth-ask-submit,
plus <!-- booth:ask ... --> comments; unknown stem left alone, not blanked
- _ask_inline.html: self-contained fragments (own scoped styles, no JS), per-question
groups bound to one form via the HTML5 form= attribute so a scattered
multi-question ask still POSTs once
- unplaced questions and a missing submit block are appended, so a partially
marked-up page can never produce an unsubmittable 400
- chip becomes a jump link to the first open ask; /asks page kept as a fallback
- 6 tests (one caught the partial-placement drop); v0.1.14
A custom index.html is returned verbatim, so booth.html's asks panel never
rendered there — a valid ask (emmie-anchor/anchor.ask.json) was listed by the
CLI and shown nowhere, with nothing to say so.
- panel extracted to _asks.html; new GET /b/<name>/asks standalone page
- verbatim pages get an amber '? N open asks' chip beside the back chip
- POST /answer honours back=asks so answering returns to that page
- single-question asks now keep an optional 'title' (was silently dropped)
- README + routes table; 8 regression tests; v0.1.12
- asks.py: single {prompt, options} and multi {title, questions:[{key, prompt, options, notes?}]} both normalise to questions[]; per-question notes; every question required on submit
- /answer reads choice.<key> / notes.<key> / notes for multi; single shape unchanged
- booth asks prints per-question picks; README + CLI header; install step symlinks the CLI to ~/.local/bin; v0.1.10; 135 tests
vh