{ "listen": ":8080", "//token_file": [ "The bearer token every request must carry. homesrv is the client and it", "is on the LAN, so this port cannot be loopback and the token is what", "stops anything else on the network spending the card or reading /slots.", "A path, never the token: mavgpud refuses to start when listen is", "reachable from the network and this is unset.", "Same value as MAVEN_GPU_TOKEN in homesrv's deploy/telegram.env." ], "token_file": "/home/kami/.config/mavgpud.token", "llama_addr": "127.0.0.1:10000", "llama_bin": "llama-server", "//llama_args": [ "E4B carries no MTP tensors, so the speculative flags are gone with the 12B.", "MTP on this box is a separate gguf of architecture gemma4-assistant with", "nextn_predict_layers=4, and mtp-gemma-4-12B-it-BF16 is the only one there is.", "Its head is trained against the 12B's hidden states, so it cannot drive E4B." ], "llama_args": [ "-m", "/mnt/D/AI/gemma4/gemma-4-E4B-it-qat-UD-Q4_K_XL.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", "--chat-template-kwargs", "{\"enable_thinking\":false}" ], "//stt": [ "CrisperWhisper 2.0 turbo, which Maven reaches directly on port 8081.", "mavgpud runs it because it is a ROCm process on this card: under its own", "systemd unit it registered on the KFD and the supervisor evicted", "llama-server every few seconds. CW2_TOKEN comes from the unit's", "EnvironmentFile and is never a flag value." ], "stt": { "addr": "127.0.0.1:8081", "bin": "/home/kami/Programs/cw2-eval/.venv/bin/python", "args": ["/home/kami/Programs/cw2-service/serve.py"] }, "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 }