Closes the one axis of the original premise left unverified. Measured
cold (cache-busted) on both builds under matching serve configs:
~6.7k-token prompt 3,206 -> 6,334 tok/s prefill (+98%)
~27k-token prompt 2,862 -> 5,085 tok/s prefill (+78%)
TTFT on a ~27k doc 9.43 -> 5.31 s (-44%)
Prefill gains far exceed the +18% decode gain, and that ordering is the
expected one: decode at bs=1 is memory-bandwidth-bound and the weights
are 4-bit under either scheme, so little changes; prefill is
compute-bound, which is where native Blackwell FP4 tensor cores replace
the Marlin dequant-to-BF16 path. The summarizer aliases are the
consumers that feel this.
Adds bench/prefill_bench.py plus the raw JSON. The harness deliberately
uses SystemRandom: a seeded nonce regenerates the previous run's prompts
verbatim, prefix caching then serves them, and the first attempt read
~41k tok/s of cache-hit rather than ~5k of actual prefill.
Re-quantizes the fleet `gen` seat from weight-only NVFP4A16 to a
mixed-precision build: NVFP4 W4A4 for layers 0-55 MLPs, FP8 W8A8 for the
attention projections / linear_attn / lm_head / layers 56-63 MLPs, FP8 KV
cache. Replicates the scheme of unsloth/Qwen3.8-27B-NVFP4 on the
abliterated weights.
The queued task named this "W4A8" (NVFP4 weights + FP8 activations). That
checkpoint cannot be served: vLLM 0.24's compressed-tensors dispatcher
(compressed_tensors.py:704-713) accepts NVFP4 weights with either no input
quantization (W4A16, which forces the Marlin kernel) or NVFP4 input
quantization (W4A4) -- anything else, FP8 included, raises ValueError at
load. CompressedTensorsW4A8Fp8 is INT4 weights gated on an exact-sm90
check, so it is closed on Blackwell twice over. The ~20% intuition was
correct; the scheme name was not. Getting FP8 into the mix has to be done
per-layer-group.
Established the gain before spending GPU time: unsloth's build was already
on-box, so serving it as a probe measured +19.1% over our seat at identical
MTP acceptance -- a kernel-level result, no requant needed to learn it.
Measured, cache-busted, bs=1:
decode 80.12 -> 94.53 tok/s (+18.0%)
MTP acceptance 47.8% -> 47.7% (unchanged)
perplexity (n=6) 6.941 -> 7.059 (+1.7%)
abliteration 4/4 -> 4/4 (preserved)
weights on disk 27.7 -> 22.5 GB (-19%)
Surface test green on the live seat: plain chat, vision, tool calling,
thinking split, 36K-token needle retrieval, streaming. All 7 LiteLLM
aliases verified routing.
GEN_GPU_MEM_UTIL 0.45 -> 0.43: the new weights are 5.2 GB smaller, and at
0.45 the seat absorbed that slack as KV, leaving meromero-charrp 0.18 GiB
short of its budget on the shared GPU0 -- it crash-looped. Handing the
space back leaves gen 422K tokens of KV (1.6x its 262K context) and both
seats co-resident at 89.8/97.9 GB.
Also records two measured negatives so they are not re-chased:
GEN_SPEC_TOKENS is already optimal at 3 (swept 2/3/4/5 -> 77.1/80.1/78.7/
75.9 tok/s), and vLLM's prompt_logprobs are ~uniform while speculative
decoding is on, so perplexity must be measured with spec off.
Pipeline, acceptance harness and raw measurements land in
services/gen-seat-mixed-quant/. Rollback is one .env line; the previous
build is untouched at /tank/aimodels/qwen38-27b-uncensored-nvfp4.
The char-rp seat shipped with no tool-call parser at all, so every
tools-bearing request was rejected outright:
400 "auto" tool choice requires --enable-auto-tool-choice and
--tool-call-parser to be set
MeroMero-v2 is Gemma-4, which emits its own native
`<|tool_call>call:name{...}<tool_call|>` syntax rather than the
qwen3_coder XML the Qwen-family seats use. vLLM 0.24 ships a matching
`gemma4` parser whose TOOL_CALL_START/END, CHANNEL_START/END and escape
token constants line up with this tokenizer's etc/eoc/escape tokens
exactly.
Three flags, and they are a set:
- --tool-call-parser gemma4 + --enable-auto-tool-choice: the fix proper.
- --reasoning-parser gemma4: without it the post-tool-response turn
leaks a literal `<|channel>thought\n<channel|>` prefix into content
(upstream vllm #45834 — the chat template leaves the prompt inside an
open channel block).
- --default-chat-template-kwargs '{"enable_thinking": false}': MANDATORY
companion to the reasoning parser. The parser reads enable_thinking
from chat_template_kwargs and defaults it to True
(vllm/parser/gemma4.py:439); True makes is_reasoning_end() return
False at a new turn, pre-initialising the engine to REASONING, which
routes ALL plain RP prose into reasoning_content and returns a null
content — breaking every char-rp consumer. This template already
defaults enable_thinking to false (chat_template.jinja:350), so
passing it explicitly renders a byte-identical prompt (verified across
plain / tools / post-tool-response / system-prompt shapes). It changes
generation not at all; it only corrects the parser state machine.
Verified green on the live seat after deploy: tool call streaming and
non-streaming, tool-result round-trip (leak gone), plain prose in
content with reasoning null, vision unchanged.
A booth of a dozen webms fetched them all at page load
(preload=metadata still pulls real byte ranges per file); nothing
loads now until the viewer hits play.
Operator-directed (Vuong 2026-08-13): migrated stonehenge-park off the nh3-docker
beta deployment to a permanent fixture on ana-docker (10.250.50.70) before the
v1.0.0 final cut. SQLite (park-data) migrated consistently (stop -> tar-copy ->
start; byte-identical). restic auto-covered by ana-docker's /var/lib/docker/volumes
source. Stable name park.phasefinal.com -> 10.250.50.70 (Cloudflare DNS-only) so
clients decouple from the host IP. Homepage tile 'The Henge' added. nh3-docker stack
left stopped as rollback pending park-dev cutover verification.
Operator-facing voice mint/audition/keeper-mark front-end (tts-dev), sited next
to The Booth in Apps — LAN/WG-internal, no auth. siteMonitor on /health verified
reachable from the homepage host (esh-docker-vm). Deployed via rsync.
New self-contained stack (FastAPI + SQLite + in-process scheduler) from
vh/stonehenge-park tag v1.0.0-beta.1, deployed to nh3-docker per park-dev's
operator-approved request. Port 8420, LAN/WG-internal; park-data volume (SQLite
sole source of truth) covered by the host's /var/lib/docker/volumes restic source.
Image built locally (no registry yet); .env carries PARK_API_KEY from the vault.
althing push to henge-crow deferred (PARK_ALTHING_CHANNEL empty) until althing-cli
is wired into the container.
The TTS path was hardwired to the parked zonos-gateway: it force-reverted the
endpoint field back to zonos :8890 on load, hardcoded model=ext-tts, and decoded
the response as Zonos-specific raw float32 PCM @ 44.1kHz. Result: quoted-text TTS
was dead once zonos was parked, and pointing the field elsewhere silently failed.
- Honor the interface: set endpoint/model/voice defaults only when a field is
empty; never rewrite a user-typed value (removed the zonos auto-revert regex).
- Add a TTS model field (ttsModel); send the UI's model instead of hardcoding.
- Playback: request standard OpenAI /v1/audio/speech mp3 and decode via
audioCtx.decodeAudioData (handles wav/mp3/ogg/flac from any endpoint).
- Defaults: endpoint = LiteLLM ext-tts alias (fleet TTS gateway), voice = nova.
wgtunnel deployed + accepted end-to-end (tunnel-dev): erebe/wstunnel v10.6.2 behind
traefik on ana-docker, Host boring.phasefinal.com (Mode A anaprod cert), --restrict-to
ana-wg:31337 (not an open relay). Mirror per fleet convention; full project in vh/wgtunnel.
56KB deep-research report on thinking-capable eRP finetunes 15-30B, weighted for
spatial/state coherence, targeting RTX PRO 6000 Blackwell (sm_120) NVFP4. Preserved
from an ephemeral Booth (gecko-65) into durable reference for the quant decision.
boring.phasefinal.com CNAME -> ana-srv1 (DNS-only) published + verified; unblocks
the wstunnel ACME cert. Operator handed over an all-zones Zone:DNS:Edit token, now
vaulted at nh3-dev/.config/cloudflare/infra-ops-dns-token — fleet DNS is self-serve.
Flip the queued-project pointer: wgtunnel is now a standalone repo, pre-seeded
after a live verification pass (ana-wg UDP/31337 endpoint, traefik TLS edge on
ana-docker, direct-A public edge). Ground truth captured in the new repo;
/vor-plan is the next step. Do wgtunnel work in ~/development/wgtunnel, not here.
Current state rewritten to session-end: secrets-broker LIVE (secret CLI + 25-item
backfill + rm/warn), stonehenge-park /park service repo stood up (vor-plan+vor-ui),
dots-tts extracted to tts-stack; NEXT PROJECT = wgtunnel (WireGuard over a plane's
wifi). Two detail files added; 2 oldest T&A entries archived. Handoff written to
/tmp/infra-ops-handoff.md for the post-clear pickup.
jackdaw-dev observation (2026-08-12): the new-namespace warning is non-blocking +
stderr, so a scripted put suppressing stderr can still mis-namespace silently.
Deliberately not blocking (domain-scoped names would misfire on auto-prefix);
revisit with an opt-in --strict flag only if scripted callers appear.
Both from jackdaw-dev feedback after a mis-namespaced item (missing host prefix)
hid under a prefix nobody searches:
- 'secret rm <name>' — delete an item by exact name (bw soft-delete to trash,
recoverable); closes the 'no delete path, append-only in practice' gap.
- 'secret put' now warns (stderr, non-blocking) when a name opens a brand-new
top-level namespace, listing existing ones + suggesting the host prefix —
catches a typo'd/missing prefix at store time.
Installed copy at ~/.local/bin/secret synced.
Scope corrected to per-dev-box (CC sessions on this box), not a fleet service; each
box duplicates the stack and backs up its own local secrets, hostname-namespaced.
CLI:
- backfill is local-only (scan this box's ~/development/*/{env.sh,.env} + ~/.config
credentials; exclude bootstrap.env/examples/AIPA-Data archives).
- large files (>6000 B) route to a bw ATTACHMENT instead of the note field
(Vaultwarden caps notes at ~10000 encrypted chars); get/verify read it back.
- backfill catches per-item failures and continues (bw errors raise BwError,
main converts to a clean exit); idempotent upsert makes re-runs safe.
Backfilled all 25 nh3-dev secret files into the infra-ops org's Default collection
(folder = hostname), every one round-trip verified (2 large via attachment, 23 via
note). README added for duplicating the stack to new dev boxes. Contract scope +
data-model sections updated (bw, org/collection, per-box).
secret put/get/list/backfill over Vaultwarden via the bw CLI. Items land in the
infra-ops org's Default collection (visible to the operator's primary account via
org share), organised by folder + <host>/<stack>/<file> naming; text in the note,
binary base64'd into a hidden field; sha256 + source metadata fields; idempotent
upsert keyed by name. Auth bootstraps from ~/.config/secrets-broker/bootstrap.env
(0600, apikey login + master-password unlock, per-invocation session).
Verified live end-to-end (create/upsert/get-note/get-field/list). Contract updated:
bw replaces rbw (rbw register 400'd undebuggably despite valid creds).
Known limitation: bw-subprocess-per-op is ~3s/call → ~15-25s/command; too slow for
a fleet-scale backfill. Next: a bw serve broker (fast + central-cred fleet model).
TTS development moves to a dedicated repo (~/development/tts-stack) so a separate
agent can own tuning/dev. Mirrors the chatterbox-fast extraction:
- stacks/dots-tts/ reduced to a pointer README (code/Dockerfile/compose/tests/env
now canonical in tts-stack).
- voices/ canonical corpus moved out to tts-stack/voices/. Blast-radius checked:
no eshpfi playbook/script reads the corpus (other voices/ refs are unrelated
host paths under /worktank/...).
- persistent-memory updated: TTS dev extracted + stood down; reverses the earlier
"corpus home = eshpfi voices/" call.
The ~15 experimental TTS compose wrappers stay here as reference (catalogued in
tts-stack/KNOWLEDGE.md). Live service on irv-ml1:8198 is unaffected (runs from a
copy on the host).
dots' prosody honors a pause only for ellipsis (~+0.43s) and period (~+0.3s);
comma/semicolon/colon/dash all run flat (~+0.03s vs no-punct), measured via a
duration-over-N-runs pause probe against the live service. Two sub-causes for
the flat clause reads: em-dashes regressed in v2 (the —→- fold made them read
as word-joiners), and semicolons were never honored by dots at all.
Operator ruled ellipsis "too much" → map semicolon, clause colon, and em-dash
to a period in _sanitize (believable ~0.3s clause pause). Guards, pinned by
tests: digit-guarded colon so times (3:45) and ratios (2:1) keep their colon;
en-dash kept folding to hyphen so numeric ranges (10–20) don't become "10.20";
a genuine ellipsis retains its strong pause.
Deployed to irv-ml1:8198 as local/dots-tts:v3 via the redeploy2 build →
:8199-test → pause-gate → cutover pattern (gate measured +0.427s, live healthy).
Curly apostrophes (ratatoskr's LLM emits typographic punctuation) made dots
mispronounce contractions ("Donut's"->"donut ess"); fold curly->ASCII before
synth, keep normalize_text on. Add server-side sentence-chunking so long turns
stop truncating at dots' ~40s single-generate cap (verified full 160s Zev).
Dockerfile: pin dots.tts==0.2.1 + torch/torchaudio==2.8.0 (upstream constraints
now pin a phantom gradio==6.17.0; float torchaudio->2.11.0 crashes the load).
LFM2.5 is </think>-delimited (opening tag in prompt); deepseek_r1 splits
reasoning into reasoning_content so content is the clean post-</think>
answer. Re-smoke: content valid JSON + reasoning_content populated. License
production-cleared (operator <$10M ruling), still out of routing per the
measurement gate.
vllm-lfm25 on ana-ml2 GPU1 :8021 (LiquidAI/LFM2.5-2.6B, util 0.09 into
unreserved slack, max-len 16384, no reasoning-parser so content is non-empty).
LiteLLM alias lfm2.5-2.6b with vendor sampling baked as default (temp 0.1;
top_k 50 + repetition_penalty 1.1 via extra_body). Eval-only, not in any
routing chain, pending operator ruling on LFM Open License production use.
Long operator-driven diagnosis: the 'broken/German/dead-air' was the Turbo T3
model over-running its generation tail (garble in final ~2-3s, worse with
length + tight sampling), NOT a language leak or OOM. Fix = server-side
max_chunk_chars=250 cap (:v2), keeping 3-4 sentence clean chunks with smooth
joins. Method (amplitude-gated voiced-ZCR), foot-guns (tail-trim unreliable,
build-context/image drift), and the flat-vs-repo divergence recorded.
Freed ~17.4GB (3090 728MiB->18.2GB free) for co-resident chatterbox-fast
(was OOMing). Detached native process; GPU mem held by multiprocessing-fork
children that orphan to init - kill children explicitly. Restore cmd +
affected consumers (asset-engine, gateway-chat) recorded.
Comment-only bump built from clean git archive of Worldtree origin/main
(578f8fc, on the b182 line). Index + clean-venv install + metadata==0.1.6
verified; muninn-dev + worldtree-dev pinged. Cleared from carried-pending.
Operator-authorized (via worldtree-dev thread 01KZE6TGRHAW) cleanup of the WT
#394 contamination: b182 deployed onto personal, all 3 preconditions verified,
reconcile --repair swept the 5,354 orphan index rows. Fresh reconcile confirms
orphan=0/missing=0/stale=0. Evidence-hold index-row half lifted+done; on-disk
generation-dir file-retention hold still stands. reconcile --repair exited rc=1
on a non-blocking worldtree-side git-staging bug (index.add on a deleted
uncommitted path) — flagged to worldtree-dev, not fixed here.
Brokkr independent verify clean (maxdiff 0.000000, no split). R42 v13
acceptance gate PASSES first time in its history: main+kb 56/90->90/90,
evictions 33->0. A2 control torn down. A3 throughput characterized at
~34 req/s (graceful queueing), with A4/util-bump/replica as levers.
A3 now backs the prod reranker alias but was launched --restart no;
docker update to unless-stopped so an ana-ml2 reboot can't silently
break the alias. Full compose-service promotion tracked as a follow-up
in the selection ledger.
The incumbent Qwen3-Reranker-0.6B was measured actively harming 80/90
fleet queries on main+knowledge_base (and inverting the bare-name region
behind Worldtree #389) — no-reranker beat it 89/90 vs 56/90. Brokkr's R43
bake-off selected BAAI/bge-reranker-v2-m3 (A3): 90/90 top-10, mean rank
0.19, multilingual (XLM-R), ~1.2 GB lighter than the incumbent.
Control arm (A2 = same Qwen weights, seq-cls head) scored identical to the
incumbent, proving the fault is a training prior, not the serving head —
which cancelled the expensive Qwen3-4B arm before it cost a GPU seat.
Cutover boundary 2026-08-06T17:37:48Z. The qwen3-reranker alias and the
:8002 backend are retained for one-edit rollback. Adds the process audit
trail at docs/pfi/reranker-selection-ledger.md.
Session (2026-08-05): 3 Booth features live+tagged (verbatim-wrap chip, .md/.txt
doc-viewer, image prev/next arrows); worldtree herald re-nudge bug -> forseti
althing-core v2.1.2; fleet-CI-resilience flip attempted end-to-end and PARKED on
an act_runner->gitea action-fetch auth blocker (infra-ops to research, deferred).
Archived the 2026-07-15/16 recent-decisions batch (8 entries) to keep the index
under the soft cap.
Zooming an image now shows ‹ / › arrows at the left/right edges that step
to the previous/next image in the booth (gallery sorted-rel order), wrapping
around, plus keyboard ←/→. Arrows are hidden when a booth has a single image.
booth_view_file computes neighbors via a new booth_image_names() helper and
passes prev_url/next_url to view.html. 3 new tests, suite 47 passing;
deployed + verified live on nh3-dev :8090.
Loose .md/.txt/.log files rendered as forced-download links in the gallery
and downloaded (or showed raw) when opened. Now they open in a readable
in-booth page via the existing /b/<name>/view route:
- .md -> rendered HTML (Python-Markdown: fenced code, tables, sane lists),
styled in an Australis .markdown-body with the viewer chrome;
- .txt/.log -> preformatted <pre> text view.
The gallery links docs to the viewer (📄) instead of a download; the view
page keeps a ⬇ (?dl=1) for saving. Files over 2 MB hand back raw. New
markdown dep (optional-import: degrades .md to text view if absent).
booth_image_view -> booth_view_file (now handles image + doc + raw-fallback).
9 new tests, suite 44 passing; deployed + verified live on nh3-dev :8090.
vh