67 lines
2.5 KiB
JSON
67 lines
2.5 KiB
JSON
{
|
|
"default": "gpu-fast",
|
|
"profiles": {
|
|
"gpu-fast": {
|
|
"id": "gpu-fast",
|
|
"label": "GPU fast",
|
|
"host": "docker-gpu.cin.su",
|
|
"docker_endpoint": "ssh://docker-gpu",
|
|
"role": "interactive",
|
|
"notes": "Main interactive RTX 4090 host for chat, 1C, code, image, audio and video tasks.",
|
|
"endpoints": {
|
|
"text": "http://docker-gpu.cin.su:8000",
|
|
"1c": "http://docker-gpu.cin.su:8081",
|
|
"translation": "http://docker-gpu.cin.su:8010",
|
|
"audio": "http://docker-gpu.cin.su:8020",
|
|
"video": "http://docker-gpu.cin.su:8030",
|
|
"image": "http://docker-gpu.cin.su:8040"
|
|
},
|
|
"model_overrides": {
|
|
"qwen3-coder-30b-a3b-instruct-q6_k": {
|
|
"base_url": "http://docker-gpu.cin.su:8081",
|
|
"served_model_name": "qwen3-coder-1c-q6",
|
|
"container_name": "llm-llama-qwen3-coder-q6-test",
|
|
"start_hint": "powershell -ExecutionPolicy Bypass -File scripts\\manage_gpu_q6_service.ps1 -Action start"
|
|
},
|
|
"qwen3-coder-30b-a3b-instruct-q4_k_m": {
|
|
"base_url": "http://docker-gpu.cin.su:8080",
|
|
"served_model_name": "qwen3-coder-1c-q4"
|
|
},
|
|
"devstral-small-2-24b-instruct-2512-q4_k_m": {
|
|
"base_url": "http://docker-gpu.cin.su:8080",
|
|
"served_model_name": "devstral-1c-q4"
|
|
}
|
|
}
|
|
},
|
|
"cpu-test": {
|
|
"id": "cpu-test",
|
|
"label": "CPU test",
|
|
"host": "docker-test.cin.su",
|
|
"docker_endpoint": "ssh://test-docker",
|
|
"role": "benchmark",
|
|
"notes": "Shared CPU Docker host for benchmark and fallback runs. Start heavyweight models manually before selecting this profile.",
|
|
"endpoints": {
|
|
"text": "http://docker-test.cin.su:18086",
|
|
"1c": "http://docker-test.cin.su:18086"
|
|
},
|
|
"model_overrides": {
|
|
"qwen3-coder-30b-a3b-instruct-q6_k": {
|
|
"base_url": "http://docker-test.cin.su:18086",
|
|
"served_model_name": "qwen3-coder-1c-q6-cpu",
|
|
"container_name": "llm-qwen3-coder-q6-cpu-test",
|
|
"start_hint": "powershell -ExecutionPolicy Bypass -File scripts\\manage_cpu_q6_service.ps1 -Action start"
|
|
}
|
|
}
|
|
},
|
|
"background": {
|
|
"id": "background",
|
|
"label": "Background",
|
|
"host": "docker-test.cin.su",
|
|
"docker_endpoint": "ssh://test-docker",
|
|
"role": "batch",
|
|
"notes": "Use for model downloads, RAG indexing, conversions and other long CPU jobs. Not selected automatically for chat.",
|
|
"endpoints": {}
|
|
}
|
|
}
|
|
}
|