Retire the vLLM service (frank-default-small, port 52625) on Dankclaw and serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge through the CIRU ROCmFPX llama.cpp runtime instead. - Build llama-server from ciru-ai/ROCmFPX tag qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) against the private TheRock ROCm 7.15 SDK in the retired ling3-ciru venv. The model card requires ROCm 7.15 for the advertised Strix Halo performance; the system ROCm 7.2.4 selects slower kernels. CK pinned at fdf4bb7fcc984811cef48ce817d89aac064b984a; generated ck/config.h + ck/version.h copied into the CK source tree so the ggml-hip build can include them. LLAMA_BUILD_WEBUI=OFF (HF bucket llama-ui returns 404; server is consumed via the OpenAI API). - New scripts/serve-frank-small.sh + frank-default-small.env: 64K ctx, one slot, f16 KV, context checkpoints, prompt cache, native depth-4 MTP on ROCm0, PromptForge DualView sidecars (FFN + GDN), temp 0.7 top-p 0.95, reasoning off. LD_LIBRARY_PATH puts the 7.15 SDK libs before any system ROCm. - Update the systemd unit description (same service name and port). - deploy.sh: update the dankclaw target comment. - Docs: new docs/ciru-activefpx-promptforge.md with the build runbook; update docs/index.md and AGENTS.md topology. - The vLLM venvs (vllm-venv, vllm-vk-venv) were moved to /home/dank/.AGENTTRASH/ on the target; the vllm-vulkan plugin and docs were removed from the repo in an earlier commit.
166 lines
5.7 KiB
Bash
Executable File
166 lines
5.7 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. Symlinks the systemd unit
|
|
# 3. Reloads systemd and restarts the service
|
|
# 4. Waits for the health endpoint and reports status
|
|
#
|
|
# Sudo: set FRANK_SUDO_PW so remote sudo reads the password from stdin
|
|
# (`sudo -S`). The passwordless restart helpers installed for the retired
|
|
# topology are obsolete and must not be used.
|
|
#
|
|
# Usage:
|
|
# ./deploy.sh <target> [--dry-run]
|
|
# FRANK_SUDO_PW=... ./deploy.sh <target>
|
|
#
|
|
# Targets (2026-08-18 topology):
|
|
# dankserver - llama.cpp FastMTP (frank-default-large.service, port 7770)
|
|
# dankclaw - CIRU ROCmFPX llama.cpp (frank-default-small.service, port 52625)
|
|
set -euo pipefail
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Target configuration
|
|
# ---------------------------------------------------------------------------
|
|
declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR SERVICE SERVICE_HEALTH DROP_CACHES HEALTH_WAIT
|
|
|
|
REMOTE_USER[dankserver]=dank
|
|
REMOTE_HOST[dankserver]=dankserver
|
|
REMOTE_DIR[dankserver]="/home/dank/vLLM"
|
|
SERVICE[dankserver]="frank-default-large"
|
|
SERVICE_HEALTH[dankserver]="http://127.0.0.1:7770/health"
|
|
DROP_CACHES[dankserver]=0
|
|
# Cold load: --no-mmap reads 15.7 GB through RAM; allow 10 minutes.
|
|
HEALTH_WAIT[dankserver]=300
|
|
|
|
REMOTE_USER[dankclaw]=dank
|
|
REMOTE_HOST[dankclaw]=dankclaw
|
|
REMOTE_DIR[dankclaw]="/home/dank/vllmScripts"
|
|
SERVICE[dankclaw]="frank-default-small"
|
|
SERVICE_HEALTH[dankclaw]="http://127.0.0.1:52625/health"
|
|
DROP_CACHES[dankclaw]=0
|
|
# CIRU llama.cpp (ROCm 7.15) loads the 34.9 GiB ActiveFPX payload + MTP
|
|
# draft and initializes PromptForge views; allow 20 minutes.
|
|
HEALTH_WAIT[dankclaw]=600
|
|
|
|
TARGET="${1:-}"
|
|
DRY_RUN=0
|
|
if [ "${2:-}" = "--dry-run" ]; then
|
|
DRY_RUN=1
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Validation
|
|
# ---------------------------------------------------------------------------
|
|
if [ -z "${TARGET:-}" ]; then
|
|
echo "Usage: $0 <dankserver|dankclaw> [--dry-run]"
|
|
exit 1
|
|
fi
|
|
if [ -z "${REMOTE_HOST[$TARGET]:-}" ]; then
|
|
echo "Unknown target: $TARGET"
|
|
exit 1
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Sudo wrapper (headless-friendly)
|
|
# ---------------------------------------------------------------------------
|
|
SUDO_PREFIX="sudo"
|
|
if [ -n "${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...'
|
|
${SUDO_PREFIX} sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'
|
|
"
|
|
fi
|
|
|
|
REMOTE_SCRIPT="
|
|
set -euo pipefail
|
|
cd '${REMOTE_DIR[$TARGET]}'
|
|
|
|
echo '[2/4] Pulling repo on ${TARGET}...'
|
|
git pull origin main
|
|
|
|
echo '[3/4] Symlink unit and restart ${SERVICE[$TARGET]}...'
|
|
${SUDO_PREFIX} ln -sf '${REMOTE_DIR[$TARGET]}/scripts/${SERVICE[$TARGET]}.service' /etc/systemd/system/${SERVICE[$TARGET]}.service
|
|
${DROP_CACHES_CMD}
|
|
${SUDO_PREFIX} systemctl daemon-reload
|
|
${SUDO_PREFIX} systemctl enable '${SERVICE[$TARGET]}'
|
|
${SUDO_PREFIX} systemctl restart '${SERVICE[$TARGET]}'
|
|
"
|
|
|
|
if [ "$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
|