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
Config-file deployment (the trial model lives in config.yaml, so /model/update refuses it):
block rewritten to run-6 reality — abliterated base, NVFP4A16 artifact, stacks/erp-seat,
no gate on this artifact by operator ruling, same-site hop. Deployed to ana-docker and the
gateway restarted; trial -> erp-tune-v6-nvfp4a16 verified end to end (3/3).
- services/erp-seat-quant/quant_nvfp4a16_gemma4_moe.py: linearize_moe first (playbook §3.15),
asserts the expert Linear count, routers/vision/audio/norms/lm_head ignored, W4A16 for RP
long-session fidelity, post-steps restore processor configs + template and reset the
tokenizer truncation cap (§3.14); --dry-run proves targets before GPU time
- services/erp-seat-quant/run_quant_erp_v6.sh: detached container on GPU1 (vllm-llmcompressor)
- stacks/erp-seat: serve recipe copied from gemma4-charrp, true served name only, port 8021
- scripts/erp-tune-gx10/pull-verify-jenerallee78.sh + base-pin-jenerallee78-shards.txt:
revision-pinned root-shard pull, 32/32 sha256+size vs brokkr-smithy pins, index
set-equal to stock, STOCK tokenizer set installed over the repo's (which bakes in
a 256-token truncation); repo originals kept as *.repo
- scripts/erp-tune-gx10/run-06-gx10.json + launch-run-06.sh: run-05 config with the
base swapped, recipe-r6, survivors-r5 verbatim, stock template path
- docs/runbooks/gx10-run-06.md: pull/verify record, free-check result (encode
reproduces run 5 exactly), hf download --include gotcha, gate naming
(erp-seat-base-ara / erp-tune-v6)
Operator-directed question (via brokkr): which weights at
/home/infra-ops/models/gemma4-26b-a4b-it-bf16 — stock or the heretic abliteration?
Answer from bytes: STOCK google/gemma-4-26B-A4B-it, byte-for-byte. Three-way match:
local shard sha256 (1127684971/aab47033) == HF download etags == stock repo LFS
oids, and download commit 4d7ae498 == stock HEAD. The recipes' -heretic-bf16 label
is a naming error (run-04 provenance was right; refusal telemetry confirmed). All
of runs 3/3c/4/5 trained from stock. Plausible cause: the selected llmfan46 26B-A4B
Heretic abliteration ships GGUF-only, so the bf16 safetensors pulled was stock.
vh