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

2026-09-17 16:45:50 +08:00
commit 5f3030260e
27 changed files with 1705 additions and 0 deletions
@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+source "$(dirname -- "${BASH_SOURCE[0]}")/common.sh"
+if [[ "${1:-}" == baseline ]]; then
+  compose+=(-f configs/baseline-32k.yaml)
+elif [[ $# -gt 0 ]]; then
+  echo "Usage: $0 [baseline]" >&2; exit 2
+fi
+"${compose[@]}" config --quiet
+"${compose[@]}" up -d --no-build vllm
+echo 'Loading takes about 10-13 minutes. Run scripts/wait.sh, then scripts/test.sh.'