scriberr to fv-ml1 GPU 3 (on-demand, steps aside to irv-ml1 A6000); intern-decision 32k-token calls (cap 14.4 GiB)

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.

persistent-memory.md

@@ -183,6 +183,10 @@ _As of 2026-09-30 ~0120 PT._
   - **Upstream PR prepared, NOT opened; it needs Prime's yes** (`stacks/scriberr/patches/upstream-pr/PR.md`).
   - **OPEN, not fixed:** Parakeet skips runs of ≥10 words mid-chunk with ANY slicer, upstream's included (12–17 runs, 500–720 words per 12 transcripts; p2 lost 85 words at today's old setting). It is chaotic with cut placement. The investigation (decoder, chunk length, model) is Prime's call.
   - Private bench data (copies of Prime's two uploads + transcripts) sits in fv-ml1 `/tank/spikes/scriberr-slicer/private/` (mode 700), kept pending Prime; the public audio and metrics are beside it.
+- **2026-09-30 1322–1335, Prime: "Go GPU 3 now and extend the jev endpoint to hit 32k tokens".** DONE.
+  - **Scriberr is on fv-ml1 GPU 3** (`SCRIBERR_GPU_ID=3`; a 20-min file verified at 5,496 MiB). It is an on-demand tenant of the reserve, like Blender: it STEPS ASIDE when a full-size seat claims GPU 3, and it goes to **irv-ml1's A6000**, NOT back to GPU 1.
+  - **intern-decision: `VRAM_CAP_GIB=14.4`, `MAX_TOKENS=32768`** (Jev's 32k). The measured card peak at the limit is 15,220 MiB (1 and 16 questions, n=3) against a 15,437 budget; 32,769 tokens → 422; latency 2.1 s at 32k. JevBench is still 202/231 with 0 diffs.
+  - ⚠ The first call in a new length bucket after a restart costs ~6.5 s (kernel autotune per shape bucket). A startup warm-up across the buckets would fix it; not done.
 - **intern-decision LIVE on fv-ml1 GPU 1 since 0941 2026-09-30, REPLACING SemIf (Prime: "replace semif with intern-decision now", with Scriberr fixed alongside).**
   - Where: `http://intern-decision.fv.internal:8033`, image `intern-decision-serve:0.1.0`, token `intern-decision/api-token`. Code and contract are in `services/intern-decision-serve/`, the stack in `stacks/intern-decision`.
   - Surface: semif-compatible `/decide`, `/decide/shared`, `/health`. It has 12 documented deltas; the main one is that the questions in one call share a prompt, in calls of at most 16.

servers/fv-ml1/README.md

@@ -181,13 +181,14 @@ embed/rerank/reward trio. GPUs are pinned per container via
 
 **GPU 1 — light / eval / retrieval + char-RP GGUF (~91/98 GB, on-demand):**
 
-> ⚠ **This table is stale (checked 2026-09-27).** Live GPU 1 residents are `scriberr`,
+> ⚠ **This table is stale (checked 2026-09-27).** Live GPU 1 residents are `vllm-coder`,
-> `vllm-coder`, `vllm-erp-seat` and `vllm-meromero-rp`.
+> `vllm-erp-seat` and `vllm-meromero-rp` (`scriberr` moved to GPU 3 on 2026-09-30 1322).
 > **`intern-decision`** joined them on 2026-09-30, 0941 PT: :8033, 8,812 MiB at rest, 9,866 MiB
-> peak, hard-capped at 9.0 GiB with `MAX_TOKENS` 7,168; see `stacks/intern-decision`. It replaced
+> peak at first; since 1330 it is capped at **14.4 GiB with `MAX_TOKENS` 32,768** (card peak 15,220 MiB at the
-> **`semif`** (:8032), which is stopped and kept as the rollback, per Prime's ruling of 2026-09-30.
+> limit), because scriberr left this card. See `stacks/intern-decision`. It replaced **`semif`** (:8032),
-> **GPU 1 budget:** nvidia-smi `Free` read 15,442 MiB before intern-decision and 6,581 MiB after,
+> whose container was removed and is kept as the rollback, per Prime's ruling of 2026-09-30.
-> at rest. That covers scriberr's 5,496 MiB peak even while intern-decision is at its own peak.
+> **GPU 1 budget:** nvidia-smi `Free` reads 6,625 MiB with intern-decision at rest. All of it is intern-decision's
+> headroom for 32k calls (217 MiB spare at its peak). Nothing else fits on this card now.
 > Measure nvidia-smi `Free` (the driver reserves 640 MiB per card) before adding anything to
 > this card. Read the host
 > (`docker inspect … DeviceRequests`), not this table. (A fixtures-only `augaman` instance ran
@@ -236,6 +237,12 @@ GPU 2 at 0.96).
 while in use (`restart: "no"`, about 270 MiB when idle with the desktop running, 0 when down).
 The reserve still stands: whenever a full-size seat takes GPU 3, Blender stays down.
 
+**GPU 3 on-demand tenant (Prime, 2026-09-30 1322): `scriberr`** (`stacks/scriberr/`). It holds 0 VRAM when
+idle and peaks at ~5.5 GB per job. Same rule as Blender: when a full-size seat claims GPU 3, Scriberr steps aside,
+and its planned landing spot is **irv-ml1's A6000** (~32 GB free on 2026-09-30, but shared with bursty ComfyUI
+work; check the peaks first). It does NOT go back to GPU 1, because GPU 1's headroom now funds intern-decision's
+32k-token calls (cap 14.4 GiB).
+
 **Retired:**
 - `llama-swap` (former GGUF multiplexer on :9292) — replaced by dedicated
   per-model seats (e.g. `llama-charrp`); no longer running.

stacks/intern-decision/.env.example

@@ -1,18 +1,19 @@
 # intern-decision — copy to /opt/docker/compose/intern-decision/.env on fv-ml1 (mode 0600).
 # Built on fv-ml1 from services/intern-decision-serve (see README "Building").
-IMAGE=intern-decision-serve:0.1.0
+IMAGE=intern-decision-serve:0.1.2
 PORT=8033
 HOST_IP=10.251.50.54
-# fv-ml1 GPU 1 = the utility card (vllm-coder, erp, meromero, scriberr).
+# fv-ml1 GPU 1 = the utility card (vllm-coder, erp, meromero). scriberr moved to GPU 3 (2026-09-30).
 GPU_ID=1
 # HARD torch-allocator cap: the single knob that holds the container's WHOLE nvidia-smi footprint
-# (CUDA context included) inside GPU 1's budget next to scriberr (infra-ops, 2026-09-30):
+# (CUDA context included, ~660 MiB outside the allocator) inside GPU 1's free memory (infra-ops,
-#   GPU 1 nvidia-smi Free >= 15,400 MiB  =  our card peak 9,876 (cap 9.0 GiB + 660 MiB outside the
+# 2026-09-30 1330): with the vLLM seats static, this container may use its rest (8,812) + GPU 1
-#   allocator, measured) + scriberr's peak 5,496, rounded up. README "VRAM".
+# nvidia-smi Free (6,625) = 15,437 MiB. 14.4 GiB cap -> card ceiling ~15,408. README "VRAM".
-VRAM_CAP_GIB=9.0
+VRAM_CAP_GIB=14.4
 # Tokens per CALL (state + up to 16 questions), checked BEFORE the forward pass: a longer call is a
-# clear 422. 7,168 is the largest call measured to fit under VRAM_CAP_GIB=9.0. Change the two TOGETHER,
+# clear 422. 32,768 = Jev's "32k for state plus the longest question"; measured to fit under 14.4 GiB
-# and re-measure (README "VRAM"): a larger value would let a call reach the cap and return 503.
+# at a card peak of 15,220 MiB (1 question and 16 questions, n=3 each). Change the two TOGETHER, and
-MAX_TOKENS=7168
+# re-measure (README "VRAM"): a larger value would let a call reach the cap and return 503.
+MAX_TOKENS=32768
 # >= 32 characters; source of truth: secret get intern-decision/api-token
 INTERN_DECISION_API_TOKEN=

stacks/intern-decision/README.md

@@ -80,7 +80,36 @@ curl -s -H "Authorization: Bearer $T" http://intern-decision.fv.internal:8033/de
      never truncated.
    - A request with more decisions is split into more calls, and each call must fit.
 
-## VRAM: fits beside scriberr's peak, whatever the request
+## VRAM: 32k-token calls since 2026-09-30 1330 (scriberr moved to GPU 3)
+
+**Current setting: `VRAM_CAP_GIB=14.4`, `MAX_TOKENS=32768`** (Prime: move scriberr to GPU 3 and "extend the jev
+endpoint to hit 32k tokens if possible"). With scriberr gone, GPU 1 holds only the static vLLM seats and this
+service. This container may therefore use its rest (8,812 MiB) plus GPU 1's nvidia-smi `Free` (6,625 MiB), which is
+**15,437 MiB**. The 14.4 GiB cap plus the ~660 MiB outside the allocator puts the card ceiling at ~15,408 MiB.
+
+Measured on the live service (per-process nvidia-smi every 0.1 s; single `noul` question unless noted; n=3, deterministic):
+
+| call tokens | card peak MiB | wall (warm) |
+|---|---|---|
+| 3,187 | 9,306 | 0.15 s |
+| 12,187 | 11,206 | 0.68 s |
+| 24,187 | 13,552 | 1.49 s |
+| 29,987 | 14,692 | 1.92 s |
+| **32,768 (limit)** | **15,220** | 2.12 s |
+| 32,765, 16 questions | 15,220 | 2.15 s |
+| 32,769 | refused 422 before the forward | 0.30 s |
+
+Spare at the limit: 217 MiB. JevBench v1.2.16 through `/v1/systemone` after the change: 202/231, with 0 answer and 0
+probability diffs against the bench's r1..r4. `/decide` is unchanged.
+
+⚠ **Cold-shape latency:** the first call in a new length bucket after a (re)start costs ~6.5 s extra
+(3,001 and 4,000 words were slow; 3,002–3,500 and 4,097–5,000 were not). The fast kernels autotune per shape
+bucket, and the result is cached in-process. Warm calls are as tabled. A startup warm-up across the buckets would
+remove it; that is not done yet.
+
+The table below is the ORIGINAL budget (9.0 GiB / 7,168 tokens, beside scriberr) and is kept for history.
+
+## VRAM (history): fits beside scriberr's peak, whatever the request
 
 **Budget (infra-ops, 2026-09-30):** GPU 1 needs nvidia-smi `Free` ≥ **15,400 MiB** before this
 service starts. That is our card peak of 9,876 MiB plus scriberr's peak of 5,496 MiB (with its

stacks/intern-decision/compose.yaml

@@ -1,5 +1,6 @@
 # intern-decision: Intern-Decision-4B (internlm, Apache-2.0) behind intern-decision-serve, on
-# fv-ml1 GPU 1 (the utility card, beside vllm-coder, the erp/meromero seats and scriberr).
+# fv-ml1 GPU 1 (the utility card, beside vllm-coder and the erp/meromero seats; scriberr moved to
+# GPU 3 on 2026-09-30 1322, Prime, to free this card's headroom for 32k-token calls).
 # Replaces semif (Prime, 2026-09-30: "replace semif with intern-decision now").
 #
 # One forward pass per call, scored by the checkpoint's OWN inference.py (sha256-pinned); the
@@ -8,8 +9,8 @@
 # fv-ml1 from that dir.
 #
 # ⚠ VRAM_CAP_GIB is a HARD cap on torch's allocator (per-process memory fraction), set so the
-#   container's WHOLE nvidia-smi footprint, CUDA context included, fits beside scriberr's peak
+#   container's WHOLE nvidia-smi footprint, CUDA context included, fits GPU 1's free memory beside
-#   (infra-ops budget, 2026-09-30); MAX_TOKENS keeps every accepted call under the cap. A request that needs more
+#   the static vLLM seats (infra-ops budget, 2026-09-30); MAX_TOKENS keeps every accepted call under the cap. A request that needs more
 #   gets 503 out_of_memory and the service stays up. See the README before changing it.
 #
 # .env (tunables): IMAGE, PORT, GPU_ID, VRAM_CAP_GIB, MAX_TOKENS, HOST_IP, INTERN_DECISION_API_TOKEN

stacks/scriberr/.env.example

@@ -19,8 +19,9 @@ SCRIBERR_BIND=0.0.0.0
 SCRIBERR_ALLOWED_ORIGINS=http://10.251.50.54:8080,http://scriberr.fv.internal:8080
 
 # ── GPU ──────────────────────────────────────────────────────────────────
-# GPU0 is fully committed to the `gen` seat; GPU1 is the one with headroom.
+# GPU 3 since 2026-09-30 (Prime): an on-demand tenant of the full-size-seat reserve; it steps aside
-SCRIBERR_GPU_ID=1
+# (to irv-ml1's A6000) when a full-size seat claims GPU 3. See compose.yaml.
+SCRIBERR_GPU_ID=3
 
 # ── Storage (on /tank — NOT the root pool, weights are multi-GB) ─────────
 SCRIBERR_DATA_DIR=/tank/scriberr/data
@@ -48,7 +49,7 @@ SCRIBERR_SECURE_COOKIES=false
 #   tab — keep the configured model on a free local seat.
 # SCRIBERR_OPENAI_API_KEY=
 
-# GPU 1 memory budget (2026-09-30). Parakeet slice length in seconds and the
+# Memory settings measured on GPU 1 (2026-09-30; still in force on GPU 3). Parakeet slice length in seconds and the
 # torch allocator mode; see compose.yaml for the measurements. Defaults apply
 # when unset; override only with a re-measured peak.
 # SCRIBERR_PARAKEET_CHUNK_SECS=120

stacks/scriberr/README.md

@@ -142,6 +142,10 @@ tab. Keep the configured model on a free local seat.
 
 ## Parakeet memory and slicing (measured 2026-09-30)
 
+> **Moved to fv-ml1 GPU 3 at 1322 on 2026-09-30 (Prime).** The GPU 1 budget below no longer binds. Scriberr is
+> an on-demand tenant of GPU 3's reserve: it steps aside to irv-ml1's A6000 when a full-size seat claims GPU 3.
+> A 20-min file was verified on GPU 3 at a 5,496 MiB peak. The settings below were not changed by the move.
+
 Scriberr shares fv-ml1 GPU 1 with intern-decision (9.0 GiB cap, 9,876 MiB card peak).
 GPU 1's nvidia-smi Free is 15,442 MiB, so the budget left for Scriberr is about 5.5 GB
 (70 MiB spare at both peaks), so the compose file sets

stacks/scriberr/compose.yaml

@@ -18,11 +18,13 @@
 #   /tank/scriberr/src/Scriberr on fv-ml1.
 #
 # ── GPU PINNING ───────────────────────────────────────────────────────────
-# Pinned to **GPU1** via explicit device_ids, per the house convention and
+# Pinned to **GPU 3** (Prime, 2026-09-30 1322) via explicit device_ids. Scriberr holds 0 VRAM
-# because GPU0 is fully committed to the `gen` seat. GPU1 shares space with
+# when idle, so it is an ON-DEMAND tenant of GPU 3's full-size-seat reserve, like Blender: when a
-# the `sec` seat, so this stack is a guest there — keep an eye on VRAM.
+# full-size seat (Flash-Next) claims GPU 3, Scriberr STEPS ASIDE. Its planned landing spot then is
+# irv-ml1's A6000, not GPU 1 (GPU 1's headroom now funds intern-decision's 32k-token calls).
+# (It was on GPU 1 until 2026-09-30, beside the vLLM seats; history in stacks/scriberr/README.md.)
 # NOTE: do NOT add `NVIDIA_VISIBLE_DEVICES=all` (as upstream's compose does).
-# It overrides the device_ids reservation and exposes both cards.
+# It overrides the device_ids reservation and exposes every card.
 #
 # All tunables live in .env — edit that, not this file.
 
@@ -70,7 +72,8 @@ services:
       # and takes out the Parakeet + Sortformer backends (WhisperX survives).
       # `copy` trades a little disk and time for it actually working.
       - UV_LINK_MODE=${SCRIBERR_UV_LINK_MODE:-copy}
-      # ── GPU 1 memory budget (2026-09-30, Prime: Scriberr shares GPU 1 with
+      # ── Memory settings, measured while Scriberr shared GPU 1 (2026-09-30; it moved to
+      # GPU 3 at 1322 the same day, so the 5.5 GB budget no longer binds, but the values stand). Prime: Scriberr shared GPU 1 with
       # intern-decision, which holds ~9.7 GB resting / 10.3 GB peak). ──────────
       # Parakeet's buffered path cuts audio into slices of this many seconds
       # (Scriberr reads it in parakeet_adapter.go for BOTH the "is this long
@@ -94,7 +97,7 @@ services:
         reservations:
           devices:
             - driver: nvidia
-              device_ids: ["${SCRIBERR_GPU_ID:-1}"]
+              device_ids: ["${SCRIBERR_GPU_ID:-3}"]
               capabilities: [gpu]
     healthcheck:
       # 127.0.0.1 rather than localhost — the IPv6-first resolution trap has
@@ -121,7 +124,7 @@ services:
       - homepage.group=AI - Studios
       - homepage.name=Scriberr
       - homepage.icon=mdi-microphone-message
-      - homepage.description=Audio/video transcription + diarization (fv-ml1, GPU1)
+      - homepage.description=Audio/video transcription + diarization (fv-ml1, GPU3)
       - homepage.href=http://10.251.50.54:${SCRIBERR_PORT}
 
 networks: