claude
8088ef9e00
make build now catches a broken supervisor on homesrv. deploy/mavgpud.json carries the owner's gemma-4-12b line with the MTP draft model, passed to llama-server untouched. The unit is a systemd user unit because sudo on the workstation wants a password; lingering is the one command left to the owner.
32 lines
765 B
JSON
32 lines
765 B
JSON
{
|
|
"listen": ":8080",
|
|
"llama_addr": "127.0.0.1:10000",
|
|
"llama_bin": "llama-server",
|
|
"llama_args": [
|
|
"-m", "/mnt/D/AI/gemma4/gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
|
|
"-md", "/mnt/D/AI/gemma4/mtp-gemma-4-12B-it-BF16.gguf",
|
|
"-ngl", "99",
|
|
"-fa", "on",
|
|
"-np", "1",
|
|
"--host", "127.0.0.1",
|
|
"--port", "10000",
|
|
"--ctx-size", "32768",
|
|
"--threads", "6",
|
|
"--batch-size", "2048",
|
|
"--ubatch-size", "512",
|
|
"--jinja",
|
|
"--spec-type", "draft-mtp",
|
|
"--spec-draft-n-max", "2"
|
|
],
|
|
|
|
"kfd_root": "/sys/class/kfd/kfd/proc",
|
|
"drm_device": "/sys/class/drm/card1/device",
|
|
|
|
"poll": "1s",
|
|
"idle_timeout": "15m",
|
|
"stop_grace": "20s",
|
|
"min_free_vram_bytes": 10737418240,
|
|
"evict_after_polls": 2,
|
|
"start_after_polls": 5
|
|
}
|