a7f453b997
- Migrate run_bench.sh from dsv4_h200_sglang_tp_dp_matrix - Add missing generate_scenarios.py, compare.py, matrix.json - Fix MODEL_PATH to /root/data/models/ds_flash_v4 - Fix DATASET_PATH to local dummy_sharegpt.json - Tune CONTEXT_LENGTH, MAX_RUNNING_REQUESTS, MEM_FRACTION_STATIC for RTX 6000D 83GB - Exclude GPU 2 due to DRAM Uncorrectable ECC hardware error
82 lines
1.6 KiB
JSON
82 lines
1.6 KiB
JSON
{
|
|
"comment": "ISL/DSL matrix for dsv4_h200_sglang_tp_dp_matrix. Y=must test, P=optional (record N on failure), N=skip.",
|
|
"mode": "Y",
|
|
"comment": "Only mandatory (Y) combinations are tested; 1M ISL is excluded per user request.",
|
|
"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"
|
|
},
|
|
"16384": {
|
|
"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"
|
|
},
|
|
"262144": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "P",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
},
|
|
"524288": {
|
|
"128": "Y",
|
|
"256": "P",
|
|
"512": "N",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
},
|
|
"1048576": {
|
|
"128": "Y",
|
|
"256": "P",
|
|
"512": "N",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
}
|
|
},
|
|
"concurrency": {
|
|
"1024": { "low": 1, "high": 128 },
|
|
"4096": { "low": 1, "high": 64 },
|
|
"16384": { "low": 1, "high": 32 },
|
|
"65536": { "low": 1, "high": 8 },
|
|
"131072": { "low": 1, "high": 4 },
|
|
"262144": { "low": 1, "high": 2 },
|
|
"524288": { "low": 1, "high": 2 },
|
|
"1048576": { "low": 1, "high": 2 }
|
|
}
|
|
}
|