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>
75 lines
1.9 KiB
JSON
75 lines
1.9 KiB
JSON
{
|
|
"anchor": 0.21875,
|
|
"cell": "tp1_mns8",
|
|
"early_stop_reason": "",
|
|
"early_stopped": false,
|
|
"exact_output_count": 121,
|
|
"feasible": true,
|
|
"interval": {
|
|
"elapsed_s": 61.294286331,
|
|
"end_mono_ns": 199668659416799,
|
|
"end_wall_ns": 1783868095785843711,
|
|
"start_mono_ns": 199607365130468,
|
|
"start_wall_ns": 1783868034491558052
|
|
},
|
|
"invariants": {
|
|
"arrival_nondecreasing": true,
|
|
"exact_output_or_failed": true,
|
|
"outcomes_cover_selected": true,
|
|
"raw_lengths_present": true,
|
|
"selected_nonempty": true,
|
|
"warmup_16": true,
|
|
"warmup_exact_16": true,
|
|
"warmup_long": true
|
|
},
|
|
"kind": "anchor",
|
|
"mns": 8,
|
|
"observed_count": 121,
|
|
"pass_rate": 0.9917355371900827,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "f585e4793a8a6a621dbfe622514743ac316e34e3e93aaa1c6ba5f1eb58e8ff2d",
|
|
"arrival_s": {
|
|
"distinct_n": 121,
|
|
"finite_n": 121,
|
|
"max": 59.78950000000005,
|
|
"min": 0.008300000000008368,
|
|
"missing_n": 0,
|
|
"n": 121
|
|
},
|
|
"count": 121,
|
|
"long_gt4096": 42,
|
|
"offered_req_s": 2.0166666666666666,
|
|
"offered_req_s_per_gpu": 2.0166666666666666,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 114,
|
|
"finite_n": 121,
|
|
"max": 8149.0,
|
|
"min": 72.0,
|
|
"missing_n": 0,
|
|
"n": 121
|
|
},
|
|
"raw_length_order_sha256": "061592e591871368954f4f80ee75cde2cfc399bd719f3f5deaad275e9af72e8b",
|
|
"request_id_order_sha256": "9b8c177ea00e5e42bd3294328201cb57addfd823913a5721714ce69646d715f4"
|
|
},
|
|
"slo_pass_count": 120,
|
|
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
|
"tp": 1,
|
|
"tpot_ms": {
|
|
"distinct_n": 121,
|
|
"finite_n": 121,
|
|
"max": 30.344350779553743,
|
|
"min": 4.4550072992088525,
|
|
"missing_n": 0,
|
|
"n": 121
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 121,
|
|
"finite_n": 121,
|
|
"max": 2038.4164949937258,
|
|
"min": 37.96417900593951,
|
|
"missing_n": 0,
|
|
"n": 121
|
|
}
|
|
}
|