Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
116 lines
1.6 KiB
JSON
116 lines
1.6 KiB
JSON
{
|
|
"burnins": 3,
|
|
"clean_seconds": 240,
|
|
"drain_seconds": 600,
|
|
"gpu_hour_limit": 6.0,
|
|
"primary_runs": 15,
|
|
"rate": 0.4725,
|
|
"schema": 1,
|
|
"waves": [
|
|
[
|
|
{
|
|
"cell": "base-r2-C00",
|
|
"gpus": [
|
|
0
|
|
]
|
|
},
|
|
{
|
|
"cell": "A3-r1-C00",
|
|
"gpus": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"cell": "A1-r2-C00",
|
|
"gpus": [
|
|
2
|
|
]
|
|
},
|
|
{
|
|
"cell": "A4-r1-A4",
|
|
"gpus": [
|
|
3
|
|
]
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"cell": "A1-r3-C00",
|
|
"gpus": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"cell": "base-r1-C00",
|
|
"gpus": [
|
|
2
|
|
]
|
|
},
|
|
{
|
|
"cell": "A3-r3-C00",
|
|
"gpus": [
|
|
3
|
|
]
|
|
},
|
|
{
|
|
"cell": "A2-r1-A2",
|
|
"gpus": [
|
|
0
|
|
]
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"cell": "base-r3-C00",
|
|
"gpus": [
|
|
2
|
|
]
|
|
},
|
|
{
|
|
"cell": "A3-r2-C00",
|
|
"gpus": [
|
|
3
|
|
]
|
|
},
|
|
{
|
|
"cell": "A4-r2-A4",
|
|
"gpus": [
|
|
0
|
|
]
|
|
},
|
|
{
|
|
"cell": "A2-r3-A2",
|
|
"gpus": [
|
|
1
|
|
]
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"cell": "A4-r3-A4",
|
|
"gpus": [
|
|
3
|
|
]
|
|
},
|
|
{
|
|
"cell": "A1-r1-C00",
|
|
"gpus": [
|
|
0
|
|
]
|
|
},
|
|
{
|
|
"cell": "A2-r2-A2",
|
|
"gpus": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"cell": "background-primary-final-C00",
|
|
"gpus": [
|
|
2
|
|
]
|
|
}
|
|
]
|
|
]
|
|
}
|