Retire vllm-awq-qwen36 (AWQ) from target maps, README, deployment, KB index, Dankserver specs, DFlash and FP8 docs. New dankserver runtime: upstream llama.cpp, port 7770, alias frank-default-small, 3x262144 ctx, DFlash Q8_0 draft, MoE experts offloaded to CPU, attention+KV on GPU (K q8_0, V f16). deploy.sh now maps dankserver to frank-default-small and symlinks its unit. models.json: dankserver baseUrl -> :7770, contextWindow -> 262144.
146 lines
4.7 KiB
Bash
Executable File
146 lines
4.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# deploy.sh — Deploy the vllmScripts repo to a target and restart its service.
|
|
#
|
|
# This script implements the second half of the git deployment workflow from
|
|
# AGENTS.md. It assumes the local changes are committed and pushed, then:
|
|
# 1. Pulls the repo on the target
|
|
# 2. Installs / enables the systemd unit
|
|
# 3. Reloads systemd and restarts the service
|
|
# 4. Waits for the health endpoint and reports status
|
|
#
|
|
# Usage:
|
|
# ./deploy.sh <target> [--dry-run]
|
|
#
|
|
# Targets:
|
|
# dankclaw - vLLM-ROCm server (frank-default-large.service, port 7770)
|
|
# dankserver - llama.cpp server (frank-default-small.service, port 7770)
|
|
#
|
|
# Example:
|
|
# ./deploy.sh dankclaw
|
|
# ./deploy.sh dankserver --dry-run
|
|
set -euo pipefail
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Target configuration
|
|
# ---------------------------------------------------------------------------
|
|
declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR SERVICE SERVICE_HEALTH
|
|
|
|
REMOTE_USER[dankclaw]=dank
|
|
REMOTE_HOST[dankclaw]=dankclaw
|
|
REMOTE_DIR[dankclaw]="/home/dank/vllmScripts"
|
|
SERVICE[dankclaw]="frank-default-large"
|
|
SERVICE_HEALTH[dankclaw]="http://127.0.0.1:7770/health"
|
|
|
|
REMOTE_USER[dankserver]=dank
|
|
REMOTE_HOST[dankserver]=dankserver
|
|
REMOTE_DIR[dankserver]="/home/dank/vLLM"
|
|
SERVICE[dankserver]="frank-default-small"
|
|
SERVICE_HEALTH[dankserver]="http://127.0.0.1:7770/health"
|
|
|
|
TARGET="${1:-}"
|
|
DRY_RUN=0
|
|
if [ "${2:-}" = "--dry-run" ]; then
|
|
DRY_RUN=1
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Validation
|
|
# ---------------------------------------------------------------------------
|
|
if [ -z "${TARGET:-}" ]; then
|
|
echo "Usage: $0 <dankclaw|dankserver> [--dry-run]"
|
|
exit 1
|
|
fi
|
|
if [ -z "${REMOTE_HOST[$TARGET]:-}" ]; then
|
|
echo "Unknown target: $TARGET"
|
|
exit 1
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Local checks (pre-flight)
|
|
# ---------------------------------------------------------------------------
|
|
cd "$(dirname "$0")/.."
|
|
if ! git diff --quiet HEAD; then
|
|
echo "FAIL: Local working tree has uncommitted changes."
|
|
echo "Commit or stash them before deploying."
|
|
exit 1
|
|
fi
|
|
if [ "$(git rev-parse --abbrev-ref HEAD)" != "main" ]; then
|
|
echo "WARN: Not on 'main'; deploying a non-main branch."
|
|
fi
|
|
|
|
echo "=== Deploying to ${TARGET} ==="
|
|
echo " host: ${REMOTE_HOST[$TARGET]}"
|
|
echo " dir: ${REMOTE_DIR[$TARGET]}"
|
|
echo " service: ${SERVICE[$TARGET]}"
|
|
echo " health: ${SERVICE_HEALTH[$TARGET]}"
|
|
echo ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Push (unless dry-run)
|
|
# ---------------------------------------------------------------------------
|
|
if [ "$DRY_RUN" = "1" ]; then
|
|
echo "[dry-run] Would push local main to origin"
|
|
echo "[dry-run] Would SSH to ${REMOTE_HOST[$TARGET]} and git pull"
|
|
else
|
|
echo "[1/4] Pushing local main to origin..."
|
|
git push origin main
|
|
fi
|
|
|
|
REMOTE="$(
|
|
printf '%s@%s' "${REMOTE_USER[$TARGET]}" "${REMOTE_HOST[$TARGET]}"
|
|
)"
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Remote: pull + install + restart
|
|
# ---------------------------------------------------------------------------
|
|
REMOTE_SCRIPT="
|
|
set -euo pipefail
|
|
cd '${REMOTE_DIR[$TARGET]}'
|
|
|
|
echo '[2/4] Pulling repo on ${TARGET}...'
|
|
git pull origin main
|
|
|
|
# Install / symlink the systemd unit
|
|
case '${TARGET}' in
|
|
dankclaw)
|
|
sudo ln -sf '${REMOTE_DIR[$TARGET]}/scripts/frank-default-large.service' /etc/systemd/system/frank-default-large.service
|
|
;;
|
|
dankserver)
|
|
sudo ln -sf '${REMOTE_DIR[$TARGET]}/scripts/frank-default-small.service' /etc/systemd/system/frank-default-small.service
|
|
;;
|
|
esac
|
|
|
|
echo '[3/4] Reload and restart ${SERVICE[$TARGET]}...'
|
|
sudo systemctl daemon-reload
|
|
sudo systemctl enable '${SERVICE[$TARGET]}'
|
|
sudo systemctl restart '${SERVICE[$TARGET]}'
|
|
"
|
|
|
|
if [ "$DRY_RUN" = "1" ]; then
|
|
echo "[dry-run] Remote commands would run:"
|
|
echo "$REMOTE_SCRIPT"
|
|
else
|
|
ssh "$REMOTE" "bash -c '$REMOTE_SCRIPT'"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Health check
|
|
# ---------------------------------------------------------------------------
|
|
if [ "$DRY_RUN" = "1" ]; then
|
|
echo "[dry-run] Would wait for health at ${SERVICE_HEALTH[$TARGET]}"
|
|
else
|
|
echo "[4/4] Waiting for health endpoint ${SERVICE_HEALTH[$TARGET]}..."
|
|
HEALTH_URL="${SERVICE_HEALTH[$TARGET]}"
|
|
for i in $(seq 1 300); do
|
|
if curl -sf "$HEALTH_URL" > /dev/null 2>&1; then
|
|
echo " Service healthy after approx $((i * 2))s"
|
|
echo ""
|
|
echo "=== Deploy complete: ${TARGET} ==="
|
|
exit 0
|
|
fi
|
|
sleep 2
|
|
done
|
|
echo "FAIL: Service did not become healthy in 600s"
|
|
exit 1
|
|
fi
|