Files
serverAppConfigs/scripts/frank-small.service
T

20 lines
621 B
Desktop File

[Unit]
Description=SGLang MiMo-V2.6-Distill-Qwen-9B-INT8 (qwen3_5 hybrid, in-checkpoint vision, no MTP) 4x151k fp8 KV (dankclaw, frank-small)
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=dank
Group=dank
# CUDA pins its staging buffers, so the process needs the memlock budget even
# though the weights themselves are copied into VRAM.
LimitMEMLOCK=infinity
Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh
Restart=on-failure
RestartSec=10
[Install]
WantedBy=multi-user.target