- New experiments/p800/dsv4_p800_sglang_tp_dp_matrix: TP8/DP1, TP4/DP2, TP2/DP4 matrix with smoke results; TP2/DP4 documents the weight-loading OOM root cause (274 GiB INT8 weights sharded only across TP group). - Launch args drop --ep-size/--chunked-prefill-size/--max-prefill-tokens/ --max-running-requests; experts fall back to TP sharding. - Move dsv4_p800_256k_4k_probe under experiments/p800/. - scripts/common: jq-free parsing fixes in adaptive_bench_lib.sh and parse_backend.py. - .gitignore: cover raw_outputs under nested platform experiment layout.
55 lines
1.2 KiB
JSON
55 lines
1.2 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 and concurrency ranges are much lower than the H20 matrix.",
|
|
"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"
|
|
}
|
|
},
|
|
"concurrency": {
|
|
"1024": { "low": 1, "high": 32 },
|
|
"4096": { "low": 1, "high": 16 },
|
|
"16384": { "low": 1, "high": 8 },
|
|
"65536": { "low": 1, "high": 4 },
|
|
"131072": { "low": 1, "high": 2 }
|
|
}
|
|
}
|