policy(gpu-power): cards are RTX 6000 Ada at 300 W — 200 W is a mild cap, plus two sm_89 placement consequences

Corrects the SKU: RTX 6000 Ada, 300 W, not the ~600 W initially recalled. That makes
200 W a cap to 67% of TGP -- the favourable part of the concave perf/watt curve, roughly
10-15% of throughput -- rather than the severe 33% cap a 600 W part would have implied,
and it very likely sits above the card's enforceable floor, so the check becomes a
formality rather than a gate.

The protective value is worth stating: four cards at 300 W uncapped is ~1200 W, which is
roughly the neighbourhood that overwhelmed a 1500 VA unit at FV with only TWO Blackwell
cards drawing. Capping to 800 W makes a repeat of today a non-event.

Two consequences that follow from Ada independent of power, and both are placement
constraints rather than details. sm_89 has native FP8 but NOT NVFP4, which is
Blackwell-only -- so the in-house NVFP4 quants that most of this fleet runs will not be
accelerated on that colo's cards, and its seats want FP8 W8A8 builds or the NVFP4
checkpoints stay at FV. And it unparks the triton-backend item, which is a hard no on
Ampere because fp8e4nv is unsupported on sm_86 and was explicitly deferred to Ada;
sm_89 has what it needs.

VRAM is 4x48 = 192 GB against fv-ml1's 391 GB, so big-model placement stays at FV. The
Flash-Next seat needs 74 GiB resident on one card and would not fit a 48 GB Ada card
even with the n-gram table offloaded -- the offload moves the table, not the experts.

docs/runbooks/fv-site-dark-20260913.md

@@ -350,6 +350,8 @@ probably a 20 A circuit -- but size it from `power.log`, not from a spec sheet.
 
 > "i believe our ada cards for the other colo are rated 600w each, we'll want them
 > power limited to 200w"
+>
+> **CONFIRMED 2026-09-13: they are RTX 6000 Ada — 300 W, not 600 W.**
 
 The generalised lesson from this outage: **decide the power envelope first and size the
 cards into it**, rather than installing cards and discovering the constraint by tripping
@@ -367,11 +369,15 @@ Three things to settle before that is a plan:
    If the floor lands above 200 W, the envelope has to come from fewer cards or a bigger
    feed, not from the cap.
 
-2. ⚠ **The 600 W figure wants confirming against the actual SKU.** The Ada parts do not
-   land there — RTX 6000 Ada is 300 W, L40/L40S 300/350 W, RTX 4090 450 W. 600 W is
-   *Blackwell* RTX PRO 6000 Workstation Edition territory. So either these are Blackwell
-   rather than Ada, or 600 W is a two-card/total figure. Read it off the device
-   (`nvidia-smi -q -d POWER`), not off a spec sheet or a recollection.
+2. ✅ **RESOLVED — RTX 6000 Ada, 300 W.** So 200 W is a cap to **67% of TGP**, which is
+   the favourable part of the curve, not the severe 33% cap a 600 W part would have
+   implied. The floor concern largely goes away too: 200 W was borderline against a
+   600 W card's minimum and is very unlikely to sit below a 300 W card's. Still worth the
+   one command, but expect it to take.
+
+   ⭐ **The protective value is real**: 4 x 300 W uncapped is ~1200 W of card, which is
+   roughly the neighbourhood that just overwhelmed a 1500 VA unit at FV with only TWO
+   Blackwell cards drawing. Capping to 800 W makes a repeat a non-event.
 
 3. ⭐ **Decode tolerates a cap far better than training does**, which is lucky given what
    this fleet mostly does. Decode is memory-bandwidth-bound; the perf/watt curve is
@@ -380,6 +386,20 @@ Three things to settle before that is a plan:
    on the first card rather than predicted, and it will hurt a prefill-heavy or training
    workload considerably more than a serving seat.
 
+### ⚠ Two placement consequences of Ada, independent of power
+
+- **sm_89 has native FP8 but NOT NVFP4** (Blackwell-only, sm_100/sm_120). Most of our
+  in-house quants are NVFP4, so **they will not run accelerated on that colo's cards.**
+  Its seats want FP8 W8A8 builds, or the NVFP4 checkpoints stay on fv-ml1. Same class of
+  constraint as the Ampere finding for irv-ml1, one generation up.
+- ⭐ **It unparks the triton-backend item.** That is a hard no on Ampere — crashes every
+  render on the A6000, `fp8e4nv` unsupported on sm_86 — and was explicitly deferred TO
+  Ada. sm_89 has the FP8 support it needs, so it becomes testable on this hardware.
+- **VRAM:** 4 x 48 GB = 192 GB, against fv-ml1's 4 x 96 = 391 GB. Big-model placement
+  stays at FV. The Flash-Next seat needs 74 GiB resident on ONE card and would not fit a
+  48 GB Ada card even with the n-gram table offloaded — the offload moves the *table*,
+  not the experts.
+
 ⚠ **PERSIST THE CAP.** A hand-set limit holds until the next reboot and then silently
 stops holding — the worst possible failure shape, because the thing that reboots the box
 is likely to be the power event the cap existed to prevent. Systemd unit, persistence