- serve-ling3-vllm.sh: wrapper around jcbtc validated run-256k.sh (TRITON_MLA, MTP K1, 256k, 6 slots, ROCr idle-fix LD_PRELOAD); sets HOST/PORT/ SERVED_MODEL_NAME=frank-default-large - frank-default-large.service: systemd unit, User=dank, port 7770
19 lines
459 B
Desktop File
19 lines
459 B
Desktop File
[Unit]
|
|
Description=vLLM Ling-3.0-flash INT4 (CIRU gfx1151) -- frank-default-large
|
|
After=network.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=dank
|
|
Group=dank
|
|
WorkingDirectory=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native
|
|
Environment="HOST=0.0.0.0"
|
|
Environment="PORT=7770"
|
|
Environment="SERVED_MODEL_NAME=frank-default-large"
|
|
ExecStart=/home/dank/vllmScripts/scripts/serve-ling3-vllm.sh
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|