c111b3a9b0
Phase 01 (LLM Tuning): - Gemma4 26B: 74.65 t/s (fast) - Qwen 35B: 61.62 t/s (balanced) - Gemma4 31B: 16.0 t/s (deep-coder) - Qwen 27B: 16.7 t/s (deep-logic) - Qwen 122B: 8.95 t/s (ultra, GPU 1 only) Phase 02 (API Engine): - FastAPI reverse proxy on port 8000 - /engine/switch hot-swap with 503 protection - config/engine_models.json as single source of truth - Replaced 4 individual .bat files with unified engine File cleanup: - scripts/ 85 files -> 9 + _archive/ - Root .bat files -> _archive/
201 lines
3.6 KiB
JSON
201 lines
3.6 KiB
JSON
[
|
|
{
|
|
"label": "ncpumoe=0",
|
|
"ncpumoe": 0,
|
|
"avg": 15.396949591766335,
|
|
"best": 20.220093309883133,
|
|
"vram": 12011,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=5",
|
|
"ncpumoe": 5,
|
|
"avg": 4.853957926040404,
|
|
"best": 4.9029479257524216,
|
|
"vram": 11945,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=10",
|
|
"ncpumoe": 10,
|
|
"avg": 20.64137159193706,
|
|
"best": 26.474940718957154,
|
|
"vram": 12020,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=15",
|
|
"ncpumoe": 15,
|
|
"avg": 13.424368433101165,
|
|
"best": 13.698684361880598,
|
|
"vram": 12018,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=20",
|
|
"ncpumoe": 20,
|
|
"avg": 10.338449574838693,
|
|
"best": 13.495275411319872,
|
|
"vram": 11530,
|
|
"nommap": true
|
|
},
|
|
{
|
|
"label": "ncpumoe=25",
|
|
"ncpumoe": 25,
|
|
"avg": 12.920348175328435,
|
|
"best": 12.99923042323437,
|
|
"vram": 11625,
|
|
"nommap": true
|
|
},
|
|
{
|
|
"label": "ncpumoe=30",
|
|
"ncpumoe": 30,
|
|
"avg": 13.251690836275145,
|
|
"best": 13.253697466971921,
|
|
"vram": 9064,
|
|
"nommap": true
|
|
},
|
|
{
|
|
"label": "ncpumoe=7",
|
|
"ncpumoe": 7,
|
|
"avg": 16.31796299658782,
|
|
"best": 23.160760806218782,
|
|
"vram": 11994,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=9",
|
|
"ncpumoe": 9,
|
|
"avg": 7.469651892205037,
|
|
"best": 10.875064047449284,
|
|
"vram": 11941,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=11",
|
|
"ncpumoe": 11,
|
|
"avg": 14.814740144776437,
|
|
"best": 15.199641279675724,
|
|
"vram": 11984,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ncpumoe=13",
|
|
"ncpumoe": 13,
|
|
"avg": 14.183175252947136,
|
|
"best": 14.427257794639086,
|
|
"vram": 12003,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "t=2",
|
|
"ncpumoe": 10,
|
|
"avg": 28.551811207068425,
|
|
"best": 28.688565545389164,
|
|
"vram": 11968,
|
|
"t": 2,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "t=4",
|
|
"ncpumoe": 10,
|
|
"avg": 30.8619310622166,
|
|
"best": 31.17677746690393,
|
|
"vram": 11972,
|
|
"t": 4,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "t=6",
|
|
"ncpumoe": 10,
|
|
"avg": 30.578454576249854,
|
|
"best": 30.971792125516313,
|
|
"vram": 11983,
|
|
"t": 6,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "t=8",
|
|
"ncpumoe": 10,
|
|
"avg": 30.529393512116172,
|
|
"best": 30.954830478128166,
|
|
"vram": 11982,
|
|
"t": 8,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "t=10",
|
|
"ncpumoe": 10,
|
|
"avg": 30.773041112229503,
|
|
"best": 31.00899077264753,
|
|
"vram": 11972,
|
|
"t": 10,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ub=256,b=1024",
|
|
"ncpumoe": 10,
|
|
"avg": 30.49319055490045,
|
|
"best": 30.691055921541377,
|
|
"vram": 11993,
|
|
"t": 4,
|
|
"ub": 256,
|
|
"b": 1024,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ub=512,b=2048",
|
|
"ncpumoe": 10,
|
|
"avg": 30.923573731331718,
|
|
"best": 31.902272031660825,
|
|
"vram": 11995,
|
|
"t": 4,
|
|
"ub": 512,
|
|
"b": 2048,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ub=512,b=4096",
|
|
"ncpumoe": 10,
|
|
"avg": 30.723820162954862,
|
|
"best": 31.065476003548053,
|
|
"vram": 11966,
|
|
"t": 4,
|
|
"ub": 512,
|
|
"b": 4096,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "ub=1024,b=2048",
|
|
"ncpumoe": 10,
|
|
"avg": 30.489888387093156,
|
|
"best": 30.982074615885946,
|
|
"vram": 11964,
|
|
"t": 4,
|
|
"ub": 1024,
|
|
"b": 2048,
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "kv=q4_0",
|
|
"ncpumoe": 10,
|
|
"avg": 30.63156129571348,
|
|
"best": 31.088674795634944,
|
|
"vram": 11988,
|
|
"t": 4,
|
|
"ctk": "q4_0",
|
|
"ctv": "q4_0",
|
|
"nommap": false
|
|
},
|
|
{
|
|
"label": "kv=q8_0",
|
|
"ncpumoe": 10,
|
|
"avg": 29.6114222576863,
|
|
"best": 30.580427895917573,
|
|
"vram": 11980,
|
|
"t": 4,
|
|
"ctk": "q8_0",
|
|
"ctv": "q8_0",
|
|
"nommap": false
|
|
}
|
|
] |