Add OpProf campaign: protocols, results, patches, run evidence (P0-P6)
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>
This commit is contained in:
@@ -0,0 +1,74 @@
|
||||
{
|
||||
"anchor": 0.49609375,
|
||||
"cell": "tp2_mns16",
|
||||
"early_stop_reason": "slo_pass_rate_unrecoverable",
|
||||
"early_stopped": true,
|
||||
"exact_output_count": 85,
|
||||
"feasible": false,
|
||||
"interval": {
|
||||
"elapsed_s": 29.202033933,
|
||||
"end_mono_ns": 201151639670622,
|
||||
"end_wall_ns": 1783869578766097690,
|
||||
"start_mono_ns": 201122437636689,
|
||||
"start_wall_ns": 1783869549564063872
|
||||
},
|
||||
"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": 16,
|
||||
"observed_count": 273,
|
||||
"pass_rate": 0.08791208791208792,
|
||||
"schema": 1,
|
||||
"selection": {
|
||||
"arrival_order_sha256": "41168f4bd02f3ef4e83b7440a3dab7458f08df9c2bbd4452fad076b4a2e0eaed",
|
||||
"arrival_s": {
|
||||
"distinct_n": 273,
|
||||
"finite_n": 273,
|
||||
"max": 59.78950000000005,
|
||||
"min": 0.008300000000008368,
|
||||
"missing_n": 0,
|
||||
"n": 273
|
||||
},
|
||||
"count": 273,
|
||||
"long_gt4096": 97,
|
||||
"offered_req_s": 4.55,
|
||||
"offered_req_s_per_gpu": 2.275,
|
||||
"raw_input_tokens": {
|
||||
"distinct_n": 253,
|
||||
"finite_n": 273,
|
||||
"max": 8149.0,
|
||||
"min": 71.0,
|
||||
"missing_n": 0,
|
||||
"n": 273
|
||||
},
|
||||
"raw_length_order_sha256": "9e38ed1766e3933dc05a7ced5d0a73fed47ce769800f0d2c10014af0ef823f28",
|
||||
"request_id_order_sha256": "a78992ce59bb3b857a7ef8844e0a690ea9dd529a659cf5edd599b63fef8b6a80"
|
||||
},
|
||||
"slo_pass_count": 24,
|
||||
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
||||
"tp": 2,
|
||||
"tpot_ms": {
|
||||
"distinct_n": 85,
|
||||
"finite_n": 85,
|
||||
"max": 56.565095488335864,
|
||||
"min": 5.2603521261925215,
|
||||
"missing_n": 188,
|
||||
"n": 273
|
||||
},
|
||||
"ttft_ms": {
|
||||
"distinct_n": 85,
|
||||
"finite_n": 85,
|
||||
"max": 11585.765292984433,
|
||||
"min": 40.21007599658333,
|
||||
"missing_n": 188,
|
||||
"n": 273
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user