Record bounded Medium GPU split and MTP comparison

This commit is contained in:
Mikei386
2026-09-20 22:42:09 +02:00
parent 3cbcf41fab
commit 635b3c4ba9
32 changed files with 5107 additions and 0 deletions
@@ -0,0 +1,10 @@
{
"label": "85-mtp2",
"ubatch": 256,
"split": "85,15",
"mtp": 2,
"prompts": [
24576
],
"minimum_headroom_mib": 448
}
@@ -0,0 +1,577 @@
[
{
"time": 1789936657.4383829,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "6964",
"total": "12288",
"temp": "48",
"util": "100",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "11272",
"total": "16303",
"temp": "55",
"util": "0",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936659.4671788,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "8424",
"total": "12288",
"temp": "48",
"util": "0",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15574",
"total": "16303",
"temp": "54",
"util": "17",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936661.4983554,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10608",
"total": "12288",
"temp": "47",
"util": "2",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15574",
"total": "16303",
"temp": "53",
"util": "0",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936663.5305703,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "52",
"util": "44",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "60",
"util": "51",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936665.5614212,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "53",
"util": "43",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "63",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936667.5952804,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "50",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "59",
"util": "51",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936669.627116,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "48",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "61",
"util": "51",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936671.6623967,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "53",
"util": "44",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "60",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936673.6930187,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "47",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "63",
"util": "51",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936675.7236755,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "44",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "60",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936677.7546844,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "53",
"util": "45",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "64",
"util": "51",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936679.785267,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "43",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "61",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936681.8165836,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "44",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "62",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936683.8488667,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10612",
"total": "12288",
"temp": "54",
"util": "45",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15590",
"total": "16303",
"temp": "64",
"util": "50",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936685.8805652,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "52",
"util": "53",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "71",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936687.911105,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "54",
"util": "52",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "73",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936689.9424007,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "54",
"util": "55",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "73",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936691.973218,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "55",
"util": "48",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "72",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936694.0040557,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "53",
"util": "65",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "74",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936696.0368607,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "54",
"util": "64",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "74",
"util": "98",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936698.0835536,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "57",
"util": "88",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "63",
"util": "0",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936700.1248791,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "55",
"util": "41",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "65",
"util": "45",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936702.155853,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "54",
"util": "47",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "62",
"util": "60",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936704.1904633,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "55",
"util": "51",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "62",
"util": "56",
"pcie_gen": "4",
"pcie_width": "16"
}
]
},
{
"time": 1789936706.2270036,
"gpus": [
{
"name": "NVIDIA GeForce RTX 3060",
"used": "10614",
"total": "12288",
"temp": "55",
"util": "42",
"pcie_gen": "3",
"pcie_width": "4"
},
{
"name": "NVIDIA GeForce RTX 5080",
"used": "15592",
"total": "16303",
"temp": "64",
"util": "44",
"pcie_gen": "4",
"pcie_width": "16"
}
]
}
]
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,75 @@
[
"--model",
"/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf",
"--mmproj",
"/models/qwen/mmproj-BF16.gguf",
"--mmproj-offload",
"--mmproj-device",
"CUDA1",
"--alias",
"qwen-medium",
"--ctx-size",
"160000",
"--flash-attn",
"on",
"--cache-type-k",
"q4_0",
"--cache-type-v",
"q4_0",
"--cache-prompt",
"--cache-ram",
"32768",
"--threads",
"6",
"--threads-batch",
"6",
"--batch-size",
"2048",
"--ubatch-size",
"256",
"--parallel",
"2",
"--kv-unified",
"--jinja",
"--reasoning",
"auto",
"--reasoning-preserve",
"--host",
"127.0.0.1",
"--port",
"5005",
"--metrics",
"--fit",
"off",
"--n-gpu-layers",
"all",
"--load-mode",
"none",
"--no-ui",
"--temperature",
"1.0",
"--top-p",
"0.95",
"--top-k",
"20",
"--device",
"CUDA0,CUDA1",
"--main-gpu",
"0",
"--split-mode",
"layer",
"--tensor-split",
"85,15",
"--spec-type",
"draft-mtp",
"--spec-draft-n-max",
"2",
"--spec-draft-type-k",
"f16",
"--spec-draft-type-v",
"f16",
"--spec-draft-p-min",
"0.05",
"--verbosity",
"3"
]