94 lines
1.7 KiB
JSON
94 lines
1.7 KiB
JSON
{
|
|
"comment": "ISL/OSL matrix for dsv4_p800_sglang_tp_dp_matrix. Y=must test, P=optional (record skipped on failure), N=skip.",
|
|
"mode": "Y",
|
|
"notes": "P800 INT8 sustains at most ~131k input tokens, so ISL stops at 131072. Concurrency ranges match the H20 matrix; scenarios that exceed server capacity are recorded as failed/skipped and the run moves on.",
|
|
"matrix": {
|
|
"1024": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"4096": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"8192": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"16384": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "P"
|
|
},
|
|
"32768": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "P"
|
|
},
|
|
"65536": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "P",
|
|
"4096": "N"
|
|
},
|
|
"131072": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "P",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
}
|
|
},
|
|
"concurrency": {
|
|
"1024": {
|
|
"low": 1,
|
|
"high": 128
|
|
},
|
|
"4096": {
|
|
"low": 1,
|
|
"high": 64
|
|
},
|
|
"8192": {
|
|
"low": 1,
|
|
"high": 64
|
|
},
|
|
"16384": {
|
|
"low": 1,
|
|
"high": 32
|
|
},
|
|
"32768": {
|
|
"low": 1,
|
|
"high": 16
|
|
},
|
|
"65536": {
|
|
"low": 1,
|
|
"high": 8
|
|
},
|
|
"131072": {
|
|
"low": 1,
|
|
"high": 4
|
|
}
|
|
}
|
|
}
|