diff --git a/scripts/frank-default-large.service b/scripts/frank-default-large.service new file mode 100644 index 0000000..f4e513b --- /dev/null +++ b/scripts/frank-default-large.service @@ -0,0 +1,18 @@ +[Unit] +Description=vLLM Ling-3.0-flash INT4 (CIRU gfx1151) -- frank-default-large +After=network.target + +[Service] +Type=simple +User=dank +Group=dank +WorkingDirectory=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native +Environment="HOST=0.0.0.0" +Environment="PORT=7770" +Environment="SERVED_MODEL_NAME=frank-default-large" +ExecStart=/home/dank/vllmScripts/scripts/serve-ling3-vllm.sh +Restart=on-failure +RestartSec=10 + +[Install] +WantedBy=multi-user.target diff --git a/scripts/serve-ling3-vllm.sh b/scripts/serve-ling3-vllm.sh new file mode 100755 index 0000000..6ae5f36 --- /dev/null +++ b/scripts/serve-ling3-vllm.sh @@ -0,0 +1,27 @@ +#!/usr/bin/env bash +# serve-ling3-vllm.sh — Launch Ling-3.0-flash CIRU INT4 vLLM (gfx1151) on Dankclaw +# +# This wrapper sources the jcbtc ling3-runtime.env (sets VENV and MODEL_PATH), +# applies our production settings (host, port, served-model-name), and hands +# off to the validated run-256k.sh launcher (TRITON_MLA, MTP K1, 256k, 6 slots, +# ROCr idle-fix LD_PRELOAD). Do not hand-roll the vllm serve command; the +# launcher carries required env vars and the ROCr override. +set -Eeuo pipefail + +PKG="/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native" + +if [ ! -f "$PKG/ling3-runtime.env" ]; then + echo "CIRU package runtime environment not found: $PKG/ling3-runtime.env" >&2 + exit 1 +fi + +set -a +# shellcheck disable=SC1091 +source "$PKG/ling3-runtime.env" +set +a + +export HOST="${HOST:-0.0.0.0}" +export PORT="${PORT:-7770}" +export SERVED_MODEL_NAME="${SERVED_MODEL_NAME:-frank-default-large}" + +exec bash "$PKG/scripts/run-256k.sh"