33 lines
851 B
Desktop File
33 lines
851 B
Desktop File
[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
|