Frank
8551bb006b
frank-small: llama.cpp CUDA (master, sm_86) on MiMo Q6_K GGUF, 2 x 262144, asymmetric KV (f16 K + q8_0 V, flash-attn pinned for the V quant)
21 lines
712 B
Desktop File
21 lines
712 B
Desktop File
[Unit]
|
|
Description=gufo (gufo-org/gufo, ROCm gfx1151) Qwen3.8-27B UD-Q8_K_XL, DFlash2 spec decode, 262144 ctx / 1 session, root systemd unit (dankclaw, frank-large, Strix Halo iGPU)
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=dank
|
|
Group=dank
|
|
# The engine pins staging buffers; keep the memlock budget unbounded so an
|
|
# RLIMIT smaller than the pinned set cannot fail the load. Parity with the
|
|
# other LLM units on this fleet.
|
|
LimitMEMLOCK=infinity
|
|
Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env"
|
|
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|