feat: initial vLLM Qwen3.6-35B-A3B-FP8 serve script with DFlash drafting on dankserver

- Podman container with CUDA GPU access
- DFlash speculative decoding via --spec-method dflash
- FP8 KV cache, 4 parallel streams, 262K context
- CPU expert offloading via --cpu-offload-gb
- systemd service for persistent runtime

scripts/serve-vllm-qwen36-dflash.sh

@@ -31,8 +31,8 @@ echo ""
 # Remove existing container if present
 podman rm -f "${CONTAINER_NAME}" 2>/dev/null || true
 
-# Run vLLM in Podman container
-exec podman run -d --name "${CONTAINER_NAME}" \
+# Run vLLM in Podman container (foreground mode for systemd)
+exec podman run --name "${CONTAINER_NAME}" \
   --device /dev/nvidia0 \
   --device /dev/nvidiactl \
   --device /dev/nvidia-uvm \
@@ -41,7 +41,6 @@ exec podman run -d --name "${CONTAINER_NAME}" \
   -v "${GPU_LIBS}:/usr/lib/x86_64-linux-gnu:ro" \
   -v "${HF_CACHE}:/root/.cache/huggingface:ro" \
   -p "${PORT}:${PORT}" \
-  --cap-add SYS_ADMIN \
   docker.io/vllm/vllm-openai:latest \
   vllm serve "${MODEL}" \
     --port "${PORT}" \
@@ -50,7 +49,7 @@ exec podman run -d --name "${CONTAINER_NAME}" \
     --gpu-memory-utilization "${GPU_MEM_UTIL}" \
     --max-num-seqs "${MAX_NUM_SEQS}" \
     --max-model-len "${MAX_MODEL_LEN}" \
-    --speculative-method dflash \
-    --speculative-model "${DRAFT_MODEL}" \
-    --num-speculative-tokens "${NUM_SPEC_TOKENS}" \
+    --spec-method dflash \
+    --spec-model "${DRAFT_MODEL}" \
+    --spec-tokens "${NUM_SPEC_TOKENS}" \
     --trust-remote-code

scripts/vllm-qwen36.service

@@ -7,6 +7,7 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
+WorkingDirectory=/home/dank/Projects/vllmScripts
 Environment="PORT=8000"
 Environment="GPU_MEM_UTIL=0.95"
 Environment="MAX_NUM_SEQS=4"
@@ -17,16 +18,7 @@ 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
+RestartSec=5
 
 [Install]
 WantedBy=multi-user.target