fleet redo 2026-08-17: retire PP+NPU, new topology
- Move all previous scripts to old/scripts/ (retired PP/NPU-era) - frank-default-large: llama.cpp FastMTP on dankserver (HauhauCS Qwen3.8-27B IQ4_XS + FastMTP 32K draft + ngram-mod, K q8_0/V f16, 128K ctx, batch 2048/ubatch 1024, port 7770) - frank-default-small: vLLM ROCm on dankclaw (Avesed Qwen3.6-35B-A3B INT8 W8A8, full 262144 ctx, no KV quant, 4 seqs, batch 16384, ngram spec, port 52625) - retarget deploy.sh (dankserver/dankclaw, inline sudo, no helpers) - docs: deployment + index + AGENTS.md + README for new topology, superseded banners on retired docs, add frank-redo-2026-08-17 runbook
This commit is contained in:
Frank committed
1 parent
136ee080c9
commit
d9af7f1d19
45 files changed
+961
-469
No files matched your search
Executable
+196
@@ -0,0 +1,196 @@
|
||||
#!/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. Drops page caches (dankclaw) and restarts the service
|
||||
# 4. Waits for the health endpoint and reports status
|
||||
#
|
||||
# Sudo: when FRANK_SUDO_PW is set, remote sudo pipes it via `sudo -S` for
|
||||
# headless runs. Otherwise plain `sudo` is used (tty or passwordless config).
|
||||
# Prefer the passwordless restart helpers installed on each target
|
||||
# (/usr/local/sbin/frank-restart-<large|small>.sh); they cover the unit
|
||||
# symlink, cache drop (dankclaw), daemon-reload, and restart in one root
|
||||
# script. See docs/deployment.md -> Passwordless restart.
|
||||
#
|
||||
# Usage:
|
||||
# ./deploy.sh <target> [--dry-run]
|
||||
# FRANK_SUDO_PW=... ./deploy.sh <target>
|
||||
#
|
||||
# Targets:
|
||||
# dankclaw - llama.cpp 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 DROP_CACHES HELPER HEALTH_WAIT
|
||||
|
||||
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"
|
||||
# Drop page caches before restart: with the model's pages fully cached, the
|
||||
# KV/graph allocation stalls at load (VRAM stuck at 28 GiB). See AGENTS.md.
|
||||
DROP_CACHES[dankclaw]=1
|
||||
# Passwordless restart helper (root-owned, installed via /etc/sudoers.d/frank-large).
|
||||
# When present, deploy.sh uses it instead of inline sudo commands.
|
||||
HELPER[dankclaw]="/usr/local/sbin/frank-restart-large.sh"
|
||||
# Health wait in iterations of 2s. Cold loads after the cache drop measured
|
||||
# at up to 17 minutes on 2026-08-13; 600 iterations = 20 minutes.
|
||||
HEALTH_WAIT[dankclaw]=600
|
||||
|
||||
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"
|
||||
DROP_CACHES[dankserver]=0
|
||||
HELPER[dankserver]="/usr/local/sbin/frank-restart-small.sh"
|
||||
HEALTH_WAIT[dankserver]=300
|
||||
|
||||
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: $TARGET"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sudo wrapper (headless-friendly)
|
||||
# ---------------------------------------------------------------------------
|
||||
# When FRANK_SUDO_PW is set, remote sudo reads the password from stdin via
|
||||
# `sudo -S`. Otherwise plain `sudo` is used (tty or passwordless config).
|
||||
SUDO_PREFIX="sudo"
|
||||
if [ -n "${FRANK_SUDO_PW:-}" ]; then
|
||||
SUDO_PREFIX="printf '%s\n' '$FRANK_SUDO_PW' | sudo -S"
|
||||
fi
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Local checks (pre-flight)
|
||||
# ---------------------------------------------------------------------------
|
||||
cd "$(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[$TARGET]}"
|
||||
)"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Remote: pull + install + restart
|
||||
# ---------------------------------------------------------------------------
|
||||
DROP_CACHES_CMD=""
|
||||
if [ "${DROP_CACHES[$TARGET]}" = "1" ]; then
|
||||
DROP_CACHES_CMD="
|
||||
echo 'Dropping page caches for reliable model load...'
|
||||
${SUDO_PREFIX} sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'
|
||||
"
|
||||
fi
|
||||
|
||||
HELPER_PATH="${HELPER[$TARGET]:-}"
|
||||
|
||||
REMOTE_SCRIPT="
|
||||
set -euo pipefail
|
||||
cd '${REMOTE_DIR[$TARGET]}'
|
||||
|
||||
echo '[2/4] Pulling repo on ${TARGET}...'
|
||||
git pull origin main
|
||||
|
||||
if [ -x '${HELPER_PATH}' ]; then
|
||||
# Passwordless restart helper (sudoers NOPASSWD) - preferred path.
|
||||
echo '[3/4] Restarting via passwordless helper ${HELPER_PATH}...'
|
||||
${SUDO_PREFIX} '${HELPER_PATH}'
|
||||
else
|
||||
echo '[3/4] Helper not installed; using inline sudo commands...'
|
||||
# Install / symlink the systemd unit
|
||||
case '${TARGET}' in
|
||||
dankclaw)
|
||||
${SUDO_PREFIX} ln -sf '${REMOTE_DIR[$TARGET]}/scripts/frank-default-large.service' /etc/systemd/system/frank-default-large.service
|
||||
;;
|
||||
dankserver)
|
||||
${SUDO_PREFIX} ln -sf '${REMOTE_DIR[$TARGET]}/scripts/frank-default-small.service' /etc/systemd/system/frank-default-small.service
|
||||
;;
|
||||
esac
|
||||
${DROP_CACHES_CMD}
|
||||
echo '[3/4] Reload and restart ${SERVICE[$TARGET]}...'
|
||||
${SUDO_PREFIX} systemctl daemon-reload
|
||||
${SUDO_PREFIX} systemctl enable '${SERVICE[$TARGET]}'
|
||||
${SUDO_PREFIX} systemctl restart '${SERVICE[$TARGET]}'
|
||||
fi
|
||||
"
|
||||
|
||||
if [ "$DRY_RUN" = "1" ]; then
|
||||
echo "[dry-run] Remote commands would run:"
|
||||
echo "$REMOTE_SCRIPT"
|
||||
else
|
||||
# shellcheck disable=SC2087
|
||||
ssh "$REMOTE" bash -s <<REMOTE_EOF
|
||||
${REMOTE_SCRIPT}
|
||||
REMOTE_EOF
|
||||
fi
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Health check
|
||||
# ---------------------------------------------------------------------------
|
||||
if [ "$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]} (via ssh)..."
|
||||
HEALTH_URL="${SERVICE_HEALTH[$TARGET]}"
|
||||
HEALTH_ITERS="${HEALTH_WAIT[$TARGET]:-300}"
|
||||
for i in $(seq 1 "$HEALTH_ITERS"); do
|
||||
if ssh "$REMOTE" "curl -sf '$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 $((HEALTH_ITERS * 2))s"
|
||||
exit 1
|
||||
fi
|
||||
Reference in new issue
Block a user