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>
66 lines
1.4 KiB
JSON
66 lines
1.4 KiB
JSON
{
|
|
"invariants": {
|
|
"clean_duration_exact": true,
|
|
"clean_failures_zero": true,
|
|
"concurrency_bounded": true,
|
|
"drain_within_timeout": true,
|
|
"manifest_no_wrap": true,
|
|
"manifest_not_exhausted": true,
|
|
"output_tokens_exact": true,
|
|
"profile_count_exact": true,
|
|
"profile_status_ok": true,
|
|
"segment_count_exact": true
|
|
},
|
|
"numeric": {
|
|
"actual_output_tokens": {
|
|
"distinct_n": 1,
|
|
"finite_n": 1094,
|
|
"max": 64.0,
|
|
"min": 64.0,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
},
|
|
"admitted_s": {
|
|
"distinct_n": 1094,
|
|
"finite_n": 1094,
|
|
"max": 416.7779763180006,
|
|
"min": 0.0008771540015004575,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
},
|
|
"completed_s": {
|
|
"distinct_n": 1094,
|
|
"finite_n": 1094,
|
|
"max": 508.61568894199445,
|
|
"min": 22.18080371801625,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
},
|
|
"input_tokens": {
|
|
"distinct_n": 964,
|
|
"finite_n": 1094,
|
|
"max": 8190.0,
|
|
"min": 4097.0,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
},
|
|
"requested_output_tokens": {
|
|
"distinct_n": 1,
|
|
"finite_n": 1094,
|
|
"max": 64.0,
|
|
"min": 64.0,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
},
|
|
"scheduled_s": {
|
|
"distinct_n": 1094,
|
|
"finite_n": 1094,
|
|
"max": 416.7779758319957,
|
|
"min": 0.0008756940078455955,
|
|
"missing_n": 0,
|
|
"n": 1094
|
|
}
|
|
},
|
|
"schema": 1
|
|
}
|