Add reproducible DGX Spark deployment for Qwen3.8 Flash Next NVFP4

This commit is contained in:
2026-09-17 16:45:50 +08:00
commit 5f3030260e
27 changed files with 1705 additions and 0 deletions
+10
View File
@@ -0,0 +1,10 @@
#!/usr/bin/env bash
source "$(dirname -- "${BASH_SOURCE[0]}")/common.sh"
for ((i=0; i<120; i++)); do
if "${compose[@]}" exec -T vllm python3 -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health',timeout=3)" >/dev/null 2>&1; then
echo READY; exit 0
fi
sleep 15
done
echo 'Startup timed out. Inspect docker compose logs vllm.' >&2
exit 1