49 lines
2.2 KiB
Bash
49 lines
2.2 KiB
Bash
#!/usr/bin/env bash
|
|
set -Eeuo pipefail
|
|
[[ ${1:-} == --go && $(hostname) == athena ]] || { echo 'Usage on Athena: vision-go.sh --go' >&2; exit 2; }
|
|
cd /opt/mike-ai/experiments/bonsai2-ab
|
|
OUT=/data/benchmarks/bonsai2-ab
|
|
ORIGINAL=$(docker ps --format '{{.Names}}' | sed -n 's/^mike-ai-llama-\(fast\|medium\|large\|ultra\|uncensored\)$/\1/p')
|
|
[[ $(wc -w <<<"$ORIGINAL") == 1 ]] || exit 1
|
|
controller() {
|
|
docker exec mike-ai-profile-controller python3 -c '
|
|
import os, sys, urllib.request
|
|
token = os.environ.get("CONTROLLER_TOKEN", "").strip()
|
|
if not token:
|
|
token = open(os.environ.get("CONTROLLER_TOKEN_FILE", "/run/secrets/controller-token"), encoding="utf-8").read().strip()
|
|
req = urllib.request.Request("http://127.0.0.1:8090" + sys.argv[1], data=b"{}", headers={"Authorization": "Bearer " + token, "Content-Type": "application/json"}, method="POST")
|
|
print(urllib.request.urlopen(req, timeout=180).read().decode())
|
|
' "$1"
|
|
}
|
|
finish() {
|
|
local rc=$?
|
|
trap - EXIT INT TERM
|
|
./case.sh vision stop || true
|
|
controller "/profiles/$ORIGINAL/activate" || true
|
|
echo "VISION_EXIT=$rc RESTORED=$ORIGINAL"
|
|
exit "$rc"
|
|
}
|
|
trap finish EXIT INT TERM
|
|
wait_health() {
|
|
local url=$1
|
|
for ((i=0;i<120;i++)); do
|
|
curl -fsS --max-time 2 "$url/health" >/dev/null 2>&1 && return 0
|
|
sleep 2
|
|
done
|
|
return 1
|
|
}
|
|
controller /profiles/fast/activate
|
|
ip=$(docker inspect mike-ai-llama-fast --format '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}')
|
|
wait_health "http://$ip:8080"
|
|
python3 vision_probe.py --base "http://$ip:8080" --model qwen-fast --output "$OUT/vision-qwen-fast.json" --go
|
|
controller /inference/stop
|
|
./case.sh vision create
|
|
./case.sh vision start --go
|
|
wait_health http://127.0.0.1:5006
|
|
nvidia-smi --query-gpu=uuid,memory.used,memory.free --format=csv,noheader,nounits > "$OUT/vision-bonsai-before-gpu.csv"
|
|
python3 vision_probe.py --base http://127.0.0.1:5006 --model bonsai2-test --output "$OUT/vision-bonsai-fast.json" --go
|
|
nvidia-smi --query-gpu=uuid,memory.used,memory.free --format=csv,noheader,nounits > "$OUT/vision-bonsai-after-gpu.csv"
|
|
python3 repeat_critical.py --base http://127.0.0.1:5006 --model bonsai2-test \
|
|
--temperature 1.0 --seeds 7,42,99 --skip-long \
|
|
--output "$OUT/recommended-bonsai-fast.json" --go
|