Frank
f93096f2bf
llama.cpp service replacing retired vllm-awq-qwen36 on port 7770 with alias frank-default-small. Wrapper sources frank-default-small.env for tunables: 3 parallel slots at 262144 ctx, draft-dflash n-max 7, KV K=q8_0 V=f16 on GPU, all MoE experts on CPU (--n-cpu-moe 40), non-expert tensors on GPU, mmproj vision + jinja. Unit: frank-default-small.service (ExecStart in dankserver repo clone /home/dank/vLLM/scripts).
14 lines
264 B
Desktop File
14 lines
264 B
Desktop File
[Unit]
|
|
Description=llama.cpp DFlash inference (frank-default-small)
|
|
After=network.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=dank
|
|
Group=dank
|
|
ExecStart=/home/dank/vLLM/scripts/serve-llama-frank-small.sh
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target |