Keep 275 W power cap at boot

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

README.md

@@ -12,7 +12,7 @@ serving Qwen3.8-Flash-Next IQ3_S on an OpenAI/Anthropic-compatible API, used fro
  ┌──────────────────┐     LAN       ┌──────────────────────────────────────────────────────┐
  │ pi coding agent  │──────────────▶│ VM 200 llm-nixos  192.168.1.67  (NixOS 26.05)          │
  │ ~/.pi/agent      │  :8080 + key  │   strata.service ── Qwen3.8-Flash-Next IQ3_S          │
- └──────────────────┘               │   2× RTX 3090 (VFIO), gpu-unlock, 250 W cap           │
+ └──────────────────┘               │   2× RTX 3090 (VFIO), gpu-unlock, 275 W cap           │
                                     │   /models  ◀── virtiofs ── /mnt/models (NVMe XFS)      │
                                     │   gpu-temp-push ──UDP :7777──▶ lovey-fans.service      │
                                     └──────────────────────────────────────────────────────┘
@@ -37,7 +37,7 @@ serving Qwen3.8-Flash-Next IQ3_S on an OpenAI/Anthropic-compatible API, used fro
 |---|---|---|
 | Host | Proxmox VE 9.2.21, kernel 7.0.14-pve, pve-no-subscription repos | [docs/proxmox-host.md](docs/proxmox-host.md) |
 | VM 200 | `llm-nixos`: NixOS 26.05, kernel 6.18, NVIDIA open 595.71, CUDA 13.2 | [docs/nixos-guest.md](docs/nixos-guest.md) |
-| GPU tuning | 250 W power cap + [gpu-unlock](https://github.com/Zagitta/gpu-unlock) (full-rate FP16/BF16) | [docs/nixos-guest.md](docs/nixos-guest.md#gpu-tuning) |
+| GPU tuning | 275 W power cap + [gpu-unlock](https://github.com/Zagitta/gpu-unlock) (full-rate FP16/BF16) | [docs/nixos-guest.md](docs/nixos-guest.md#gpu-tuning) |
 | Inference | [Strata](https://github.com/Niko1221/Strata) @ `4b9e05a2`, Qwen3.8-Flash-Next IQ3_S | [docs/strata.md](docs/strata.md) |
 | Client | pi coding agent 1.4.0 | [docs/pi-client.md](docs/pi-client.md) |
 | Fans | `lovey-fans.py` on the host, fed GPU temps by the guest | [docs/proxmox-host.md](docs/proxmox-host.md#fan-control) |

docs/changelog.md

@@ -6,8 +6,9 @@ Newest first. Each entry: what broke, the cause, and what fixed it.
 
 With the case closed, alternating runs (250/275/250/275, fresh restart each) gave +4.6% prompt speed at
 16K at 275 W (2,892 → 3,023 tok/s) and +1.6% at 4K; decode was unchanged within noise. Peak temps went
-from 51/59°C to 53/63°C. The cap is **runtime only** (`nvidia-smi -pl 275`), and
-`nvidia-power-limit.service` still sets 250 W at boot. Results:
+from 51/59°C to 53/63°C. **Kept:** `nvidia-power-limit.service` in
+[`nixos/configuration.nix`](../nixos/configuration.nix) now sets 275 W at boot (applied with
+`nixos-rebuild switch`; Strata kept running). Results:
 [benchmarks/standard](../benchmarks/standard/README.md#power-cap-250-w-vs-275-w).
 
 ## 2026-10-26 (night): first standard benchmark and tuning arms

docs/nixos-guest.md

@@ -43,6 +43,11 @@ Dense 8192³ GEMM, torch 2.14 / cu130:
 A stock 3090 peaks at about 71 TFLOPS. The 250 W cap costs ~30% of matmul (prefill) throughput;
 decode is bandwidth-bound and barely changes.
 
+The cap is **275 W** since 2026-10-27. In Strata's benchmark, 275 W vs 250 W gave +4.6% prompt tok/s at
+16K, unchanged decode, and +2–4°C (see
+[benchmarks/standard](../benchmarks/standard/README.md#power-cap-250-w-vs-275-w)). Strata's real gain is far smaller
+than the GEMM numbers above suggest, because much of each request isn't matmul-bound.
+
 ## Temps
 
 4-minute dual-GPU BF16 burn at 250 W: GPU0 34→45°C, GPU1 44→55°C (still creeping), fans ~36%.
@@ -57,7 +62,7 @@ GPU1 runs ~10°C warmer than GPU0 (loop order or block contact). Plenty of headr
    repo. Keep the **generated** `hardware-configuration.nix` (its disk UUIDs are new) but add the
    `/models` virtiofs entry from the copy here.
 4. `nixos-install`, reboot, detach the ISO.
-5. Check: `nvidia-smi` shows both 3090s at 250 W, `ls /models`, `systemctl status gpu-temp-push`
+5. Check: `nvidia-smi` shows both 3090s at 275 W, `ls /models`, `systemctl status gpu-temp-push`
    and `journalctl -u lovey-fans` on the host shows a GPU temperature.
 6. Install Strata: [strata.md](strata.md#rebuild).
 

nixos/configuration.nix

@@ -41,7 +41,7 @@
     nvidiaPersistenced = true;
     nvidiaSettings = false;
   };
-  # Cap both 3090s at 250 W (default 350 W); reapplied on every boot
+  # Cap both 3090s at 275 W (default 350 W); reapplied on every boot. 275 vs 250: +4.6% prompt tok/s, see benchmarks/standard
   systemd.services.nvidia-power-limit = {
     description = "Set NVIDIA GPU power limit";
     after = [ "nvidia-persistenced.service" ];
@@ -50,7 +50,7 @@
     serviceConfig = {
       Type = "oneshot";
       RemainAfterExit = true;
-      ExecStart = "${config.hardware.nvidia.package.bin}/bin/nvidia-smi -pl 250";
+      ExecStart = "${config.hardware.nvidia.package.bin}/bin/nvidia-smi -pl 275";
     };
   };
   # lovey's fan daemon (lovey-fans) can't see passed-through GPUs; send it the hottest one every 2 s