The :8033 seat now serves h2oai/h2o-lightning-4b @ b43f759b on vLLM 0.30.0 with
byte-pinned KV (4.48 GiB, 135,558 tokens) behind services/h2o-decision-front:
32k refuse-not-trim admission, the seat's bearer token, and /decide +
/decide/shared translated onto /v1/systemone for albok-nemi's judge. URL, port,
token and stack name are unchanged. INC down 13:08:18, h2o healthy 13:11:27.
Post-checks on the live seat: /health at the pinned revision; JevBench public
205/231 (= bench); 422 over the cap; 16q at the cap warm 2.0-2.16 s; seat peak
16,164 MiB under 4 concurrent 16q x 32k calls against a 16,847 budget.
compose.inc.yaml + rollback-to-inc.sh restore Intern-Decision-4B in one step.
The temporary GPU 3 eval seat (stacks/h2o-eval) is down.
Layout: GPU 0 = cyberprev (KV 16 -> 15 GiB, 1.29x), erp-seat (moved from
GPU 1, KV 8.49 -> 5.5 GiB, 1.32x), voices (ctx 8,192 -> 40,960, its native
maximum, KV 6 GiB, 1.07x), coder (moved from GPU 1, ctx 16,384 -> 32,768,
the card maximum, 2.35x), parakeet-nemo. GPU 1 = gen-small (moved from
GPU 0, 5.5 GiB, 1.76x), meromero-rp (22 GiB, 1.32x), intern-decision.
Sizing rule: KV >= 1.25x max context rounded up to 0.5 GiB, checked against
7 days of LiteLLM traffic and the engines' own KV-usage logs. Each card keeps
spare memory for its bursty tenant (parakeet's cap on GPU 0, intern-decision's
32k call on GPU 1). YaRN extensions are not enabled: they do not fit, and the
Qwen cards warn static YaRN degrades short prompts.
gen-small gets --override-generation-config max_new_tokens 32768. It applies
only to requests that omit max_tokens (vLLM get_max_tokens) and answers 9
runaway ~260k-token replies in 7 days; the longest normal reply was 6,357.
Applied with playbooks/fv-ml1-rebalance-20261005.yaml (boot-check guard and
health/KV verification per seat); all nine seats healthy, gateway smoke
tests pass.
meromero-rp sized its KV from --gpu-memory-utilization, and vLLM's profile
counts co-booting neighbours as its own non-torch memory. Three boots gave
20.37 / 26.74 / 29.04 GiB of KV, and the 2026-10-05 Docker-move restart cut
GPU 1 free memory to 3,981 MiB, below intern-decision's 32k-token budget.
Coder read negative KV on every co-boot. Both are now pinned, so util only
gates the boot check (meromero util 0.52 -> 0.47, just above its footprint).
GPU 0 plateaus at ~60 MiB free 1-2 days after a boot (Beszel), so
gen-small's KV drops to 5.5 GiB (461,215 tokens, 1.76x) and parakeet-nemo
stays on GPU 0 with room for its 3,840 MiB cap. GPU 3 stays clear.
Applied with playbooks/fv-ml1-kv-pin-20261005.yaml: GPU 1 free 3,981 ->
11,801 MiB, GPU 0 495 -> 5,039 MiB right after boot; all nine seats healthy.
The ~6.5-9 s first-call-per-bucket autotune lived in the container's writable
layer and died on every recreate. 0.1.3 creates /tmp/triton-cache in the image
owned by 10001 so the named volume intern-decision_triton-cache inherits a
writable mount point, and compose mounts it.
Bucket model PROVEN, not inferred: 2,048-token buckets, 16 up to 32,768. After
one warmed call per bucket, 12 random sizes across 8k-32k were all warm (worst
2.09 s); cold entries cost 6.5-9 s. Full cold warm-up 109 s; warm re-run 17 s.
scripts/intern-decision-warmup: one noul call per bucket, MAX_TOKENS from
/health, two-point live calibration of the tokenizer's linear token model (a
single probe overcorrects and the aim oscillates around the bucket edge),
per-bucket wall times, non-zero exit on a missed bucket. Run it after an IMAGE
CHANGE only; the volume carries ordinary recreates (measured: force-recreate,
then a warmed 32k call answered in 2.11 s).
Acceptance on 0.1.3: JevBench 202/231, hard 83/111, 0 diffs / 924; warm 32k GPU
1 peak 15,218 MiB (budget 15,220; a COLD autotune touched 15,224 once, README
caveat); /decide answers. Artifacts in the acceptance dir.
Prime 2026-09-30: move scriberr to GPU 3 and extend the Jev endpoint to 32k tokens.
Scriberr holds 0 VRAM idle; verified a 20-min job on GPU 3 at 5,496 MiB. With GPU 1
freed, intern-decision's measured card peak at MAX_TOKENS=32768 is 15,220 MiB against
a 15,437 MiB budget (n=3, 1 and 16 questions); 32,769 tokens is refused 422 up front.
JevBench v1.2.16 via /v1/systemone unchanged: 202/231, 0 diffs vs the bench.
intern-decision deployed 0941 PT (cap 9.0 GiB, MAX_TOKENS 7168). Live acceptance: positive
control 240/259 and Wyrd 79/84, bit-identical to the bench (0/560 rows, Δp 0); negative control
10/122/14; largest accepted requests 200 with no 503; per-process 8,812 MiB at rest and 9,866 peak;
GPU 1 Free 15,442 before and 6,581 after (lowest 5,569 under load). Latency from nh3-dev:
21 criteria 114 ms, 16 over ~3,900 tokens 238 ms. semif README banner now REPLACED with the
rollback; fv-ml1 GPU 1 note updated.
Both are required in compose because they are coupled: MAX_TOKENS is checked before the forward
pass, so an oversized call is a clear 422 instead of reaching the cap as a 503. Pre-deploy floor
is nvidia-smi Free >= 15,400 MiB on GPU 1 (card peak 9,876 + scriberr 5,496).
stacks/intern-decision: compose (GPU 1, :8033, hard VRAM cap as the single .env knob,
healthcheck, Homepage group 'AI - Eval & Retrieval'), .env.example and README.
dns: intern-decision.fv.internal -> fv-ml1 (synced to ana/esh/nh3).
acceptance on fv-ml1 GPU 3, 3 fresh processes: bit-identical to the Jev bench's native rows
(pooled 240/259, Wyrd 79/84, 0/560 flips, Δp 0), negative control 10/122/14, 0 flips across
restarts; largest accepted request 200 at a 10,134 MiB card peak under a 9.25 GiB cap; 503 and
recovery proven at a tight cap. GPU 1 deploy held: nvidia-smi Free on GPU 1 is 15,442 MiB.
vh