Initial commit: Complete deployment scripts, power governor, systemd units, and architecture documentation for Turing multi-GPU LLM rig

2026-09-01 01:55:19 +00:00
commit aeb72cecfa
13 changed files with 1925 additions and 0 deletions
@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+# ==============================================================================
+# GPU Persistence Mode and Power Cap Tuner
+# Sets safe 150W power cap on CMP 50HX cards and activates persistence mode.
+# ==============================================================================
+set -euo pipefail
+
+echo "==> Enabling NVIDIA Persistence Mode..."
+nvidia-smi -pm 1
+
+echo "==> Setting 150W Power Cap on CMP 50HX GPUs (index 1 and 2)..."
+nvidia-smi -i 1,2 -pl 150
+
+echo "==> Resetting GPU clocks to unconstrained boost..."
+nvidia-smi -rgc
+
+echo "==> Current GPU States:"
+nvidia-smi --query-gpu=index,name,power.draw,power.limit,clocks.gr,clocks.mem --format=csv