Add vLLM serve script, systemd service, and validation test for Qwen3.6-35B-A3B-FP8 on dankserver

scripts/vllm-qwen36.service

@@ -0,0 +1,32 @@
+[Unit]
+Description=vLLM Qwen3.6-35B-A3B-FP8 with DFlash Drafting (Podman)
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=dank
+Group=dank
+Environment="PORT=8000"
+Environment="GPU_MEM_UTIL=0.95"
+Environment="MAX_NUM_SEQS=4"
+Environment="MAX_MODEL_LEN=262144"
+Environment="KV_CACHE_DTYPE=fp8"
+Environment="NUM_SPEC_TOKENS=8"
+ExecStart=/home/dank/Projects/vllmScripts/scripts/serve-vllm-qwen36-dflash.sh
+ExecStop=/usr/bin/podman stop vllm-qwen36-dflash
+ExecStopPost=/usr/bin/podman rm -f vllm-qwen36-dflash
+Restart=on-failure
+RestartSec=10
+TimeoutStopSec=60
+
+# Ensure GPU devices are available
+DevicePolicy=closed
+DeviceAllow=/dev/nvidia0 rwm
+DeviceAllow=/dev/nvidiactl rwm
+DeviceAllow=/dev/nvidia-uvm rwm
+DeviceAllow=/dev/nvidia-uvm-tools rwm
+DeviceAllow=/dev/nvidia-modeset rwm
+
+[Install]
+WantedBy=multi-user.target