diff --git a/docs/runbooks/fv-site-dark-20260913.md b/docs/runbooks/fv-site-dark-20260913.md index bf3cbb8..8fa1070 100644 --- a/docs/runbooks/fv-site-dark-20260913.md +++ b/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 diff --git a/persistent-memory.md b/persistent-memory.md index 1ecdb58..741d979 100644 --- a/persistent-memory.md +++ b/persistent-memory.md @@ -207,7 +207,7 @@ last, and do NOT restart the MTP campaign. ## Recent decisions -- `[2026-09-13]` ⭐ **STANDING POLICY (operator): cap GPU power limits at BUILD time, not after discovering the constraint.** Cards for the **other colo** — operator believes Ada, rated ~600 W each — are to be **power-limited to 200 W**. 4x200 W = 800 W of card, which fits a real circuit with a real UPS. This is the generalised lesson of the FV outage: decide the power envelope first and size the cards into it. ⚠ **200 W may be below the card's enforceable floor** — `nvidia-smi -pl` is bounded by `Min Power Limit`, often ~half of TGP on a high-TGP part, and a sub-floor request is refused (possibly quietly); run `nvidia-smi -q -d POWER | grep -iE 'power limit|default'` FIRST. ⚠ **The 600 W figure needs confirming against the real SKU** — Ada parts do not land there (RTX 6000 Ada 300 W, L40/L40S 300/350 W, 4090 450 W); 600 W is Blackwell RTX PRO 6000 Workstation territory, so these may be Blackwell or 600 W may be a two-card total. Read it off the device, not a spec sheet. ⭐ **Decode tolerates caps far better than training** (memory-bandwidth-bound; ~60-70% TGP ≈ 10-15% throughput cost, concave curve) — a 33%-of-TGP cap is deeper into the steep region and should be measured on the first card. ⚠ **PERSIST the cap** (systemd unit + persistence mode, ordered before Docker): a hand-set limit stops holding at the next reboot, which is likely to be the very power event it existed to prevent. → `docs/runbooks/fv-site-dark-20260913.md` +- `[2026-09-13]` ⭐ **STANDING POLICY (operator): cap GPU power limits at BUILD time, not after discovering the constraint.** Cards for the **other colo** are **RTX 6000 Ada, 300 W** (confirmed 2026-09-13; an initial ~600 W recollection was wrong), to be **power-limited to 200 W**. 4x200 W = 800 W of card, which fits a real circuit with a real UPS. This is the generalised lesson of the FV outage: decide the power envelope first and size the cards into it. At 300 W TGP, 200 W is a **67% cap — the favourable part of the concave perf/watt curve, ~10-15% throughput cost**, not the severe 33% cap a 600 W part would have meant; and 200 W is very unlikely to sit below a 300 W card's enforceable floor (still confirm with `nvidia-smi -q -d POWER | grep -iE 'power limit|default'`). ⭐ 4x300 W uncapped ≈ 1200 W of card — roughly what overwhelmed a 1500 VA unit at FV with only TWO Blackwell cards drawing; capping to 800 W makes a repeat a non-event. ⭐ **Decode tolerates caps far better than training** (memory-bandwidth-bound, concave curve). ⚠⚠ **Ada is sm_89: native FP8 but NO NVFP4** (Blackwell-only) — most of our in-house quants are NVFP4 and will NOT run accelerated there; that colo's seats want FP8 W8A8, or NVFP4 checkpoints stay on fv-ml1. ⭐ **This unparks [[parked_triton_backend_ampere_fp8]]** — a hard no on Ampere (fp8e4nv unsupported sm_86), explicitly deferred TO Ada, and sm_89 has the FP8 support it needs. **VRAM 4x48 = 192 GB** vs fv-ml1's 391 GB, so big-model placement stays at FV (Flash-Next needs 74 GiB resident on ONE card — the offload moves the table, not the experts). ⚠ **PERSIST the cap** (systemd unit + persistence mode, ordered before Docker): a hand-set limit stops holding at the next reboot, which is likely to be the very power event it existed to prevent. → `docs/runbooks/fv-site-dark-20260913.md` - `[2026-09-13]` ⚠⚠⚠ **FV SITE DARK — every Fountain Valley address including the BMC went unreachable ~2.5 min into a two-card load test; all other sites healthy. Operator's leading hypothesis: the 1500 VA Eaton UPS overloaded and DIED.** It fits better than a breaker trip because a UPS's output rating sits far below the circuit's, making it the first protective device to give — which explains why the site let go at **two** cards loaded rather than four, and why the ~25 W OPNsense box died with it. ⚠ **Will not self-recover** (tripped needs a human, dead needs replacing) — do NOT poll FV. ⚠ **Do NOT use surge-only outlets to exceed a UPS rating**: both banks share one NEMA 5-15P inlet rated 12 A total; the surge bank bypasses the inverter, not the current limit. ⭐ **Recover `/tank/aimodels/flash-next-mtp-bench/power.log` FIRST** — all four cards every 10 s to the cut, on `/tank` not in a container, and the ONLY load measurement that exists. ⚠ **19 of 30 gateway aliases dark and NO local fallback** — every free local model was on fv-ml1, irv-ml1 runs no chat seat at all; the only non-fv chat backends are paid, and any coverage must be a NEW opt-in alias, never a silent repoint. ⭐ **OOB design gap**: OPNsense-as-subnet-router covers box-down/gateway-up and nothing for a site-wide loss, since the BMC's only route out is that gateway. ⚠ Recovery hazard: ten `restart: unless-stopped` vLLM containers will all load at once on power-up — mask Docker first, then `compose up -d` seat by seat (which also finishes the stale-homepage-label fix, since labels attach only at creation). → `docs/runbooks/fv-site-dark-20260913.md`, `persistent-memory.d/2026-09-13-flash-next-seat-and-fv-outage.md` - `[2026-09-13]` ⭐⭐ **Qwen3.8-Flash-Next serving on ONE card with its 51B n-gram table in host RAM — the first seat whose weights do not fit its GPU.** `stacks/flash-next-seat/`, fv-ml1 GPU 2 `:8022`, plus a `gen-large` LiteLLM alias. Measured: 74.36 GiB weights resident, 14.00 GiB KV = 560,654 tokens at the full 262,144 context, 67 GiB host RSS, 75.5/212.3/387.8 tok/s at conc 1/4/8 (⚠ n=1). ⭐ The offload is vLLM **#54371 (UVA, merged 2026-09-09)** which **supersedes the paused #53899** — it has no worker process, so #53899's whole bug family (TP=1 deadlock #53960, `pidfd_getfd`/ptrace gate, stale-output-under-graphs) is designed out; in `v0.29.1rc0`, **not** `v0.29.0`. ⚠ **`text_config.ple_embedding_dtype` is the load-or-fail discriminator** for any community build. ⚠⚠ **`--kv-cache-memory` makes vLLM SKIP MEMORY PROFILING and ignore `--gpu-memory-utilization`** — 16 GiB nearly OOM'd on a 155K prefill with no visible failure; 14 GiB is the measured-safe value and vLLM's own "17.46 GiB to fully utilize" is 3.5 GiB too high. ⚠ MTP is off **pending measurement here, not written off** — the recipe's number is cross-harness and tested k=3 only, while the head is ONE layer run autoregressively, so k=1 is unpublished and may win (`services/flash-next-mtp-bench/`, one `off_A` rep banked before the outage). ⚠ A container once ran `(healthy)` with `PORTS=[]` — verify `docker port`, not the healthcheck. → `persistent-memory.d/2026-09-13-flash-next-seat-and-fv-outage.md`