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:
2026-07-13 11:06:10 +08:00
parent 607e88da3c
commit d5b276180d
412 changed files with 125056 additions and 0 deletions

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.016055910008, "kind": "anchor", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.016055910008,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 301,
"feasible": true,
"interval": {
"elapsed_s": 60.445619611,
"end_mono_ns": 207596969411260,
"end_wall_ns": 1783876024095838081,
"start_mono_ns": 207536523791649,
"start_wall_ns": 1783875963650218795
},
"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": 301,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "42c88c970510ae1b49ebcf10d2a9fb9bbc07c2ec2761dfd19193a6962cab1273",
"arrival_s": {
"distinct_n": 300,
"finite_n": 301,
"max": 59.75439999999999,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 301
},
"count": 301,
"long_gt4096": 95,
"offered_req_s": 5.016666666666667,
"offered_req_s_per_gpu": 1.2541666666666667,
"raw_input_tokens": {
"distinct_n": 283,
"finite_n": 301,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 301
},
"raw_length_order_sha256": "d1765a9ae2785d90f135e114ce1d802dec58e86fd36152182dee987a73d1604c",
"request_id_order_sha256": "2d680e08c068237fadfff567b3fb7f55a8e0a0121c009cefa07ee2653093e700"
},
"slo_pass_count": 301,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 301,
"finite_n": 301,
"max": 7.6074999528863705,
"min": 3.489643448778597,
"missing_n": 0,
"n": 301
},
"ttft_ms": {
"distinct_n": 301,
"finite_n": 301,
"max": 479.98269999516197,
"min": 36.43614600878209,
"missing_n": 0,
"n": 301
}
}

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.016591107009, "kind": "anchor", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.016591107009,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 308,
"feasible": true,
"interval": {
"elapsed_s": 61.479843593,
"end_mono_ns": 207463713361534,
"end_wall_ns": 1783875890839788527,
"start_mono_ns": 207402233517941,
"start_wall_ns": 1783875829359945005
},
"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": 308,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "860d2ac188790a401e93d3f99b9f37d6d69f0dfda1af94c37bc0067278444632",
"arrival_s": {
"distinct_n": 307,
"finite_n": 308,
"max": 59.75439999999999,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 308
},
"count": 308,
"long_gt4096": 96,
"offered_req_s": 5.133333333333334,
"offered_req_s_per_gpu": 1.2833333333333334,
"raw_input_tokens": {
"distinct_n": 288,
"finite_n": 308,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 308
},
"raw_length_order_sha256": "c533dffff00fdea5f5492826549ca09fa62fe46ef98942928115816f92a38771",
"request_id_order_sha256": "2407501cda53bf9c761c448dc50ab4780b4a55958cc00ba1b19cd09de1cf73e1"
},
"slo_pass_count": 308,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 308,
"finite_n": 308,
"max": 12.594227795259968,
"min": 3.8338481023720665,
"missing_n": 0,
"n": 308
},
"ttft_ms": {
"distinct_n": 308,
"finite_n": 308,
"max": 1612.671570997918,
"min": 38.93829099251889,
"missing_n": 0,
"n": 308
}
}

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.017126304009, "kind": "anchor", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.017126304009,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 317,
"feasible": true,
"interval": {
"elapsed_s": 60.482683353,
"end_mono_ns": 207663639929087,
"end_wall_ns": 1783876090766355953,
"start_mono_ns": 207603157245734,
"start_wall_ns": 1783876030283672912
},
"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": 317,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "37e0795a537a347b17e01cbe56e581172f28f709c8a9fc527cd2e149ef427a11",
"arrival_s": {
"distinct_n": 316,
"finite_n": 317,
"max": 59.75439999999999,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 317
},
"count": 317,
"long_gt4096": 98,
"offered_req_s": 5.283333333333333,
"offered_req_s_per_gpu": 1.3208333333333333,
"raw_input_tokens": {
"distinct_n": 295,
"finite_n": 317,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 317
},
"raw_length_order_sha256": "4edec9417636579f3ebf9140d418b8072a89f80362751426a578737870179a9c",
"request_id_order_sha256": "93cd99ebf2a760cc440dce0cb7e51273686dcfbfb07650d27e9e16d2ff1d2eed"
},
"slo_pass_count": 317,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 317,
"finite_n": 317,
"max": 7.4181628267291755,
"min": 3.5225878738684533,
"missing_n": 0,
"n": 317
},
"ttft_ms": {
"distinct_n": 317,
"finite_n": 317,
"max": 437.27293200208806,
"min": 36.18798102252185,
"missing_n": 0,
"n": 317
}
}

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.034252608017, "kind": "anchor", "pass_rate": 0.17833333333333334, "feasible": false}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.034252608017,
"cell": "tp4_mns8",
"early_stop_reason": "slo_pass_rate_unrecoverable",
"early_stopped": true,
"exact_output_count": 184,
"feasible": false,
"interval": {
"elapsed_s": 25.123306736,
"end_mono_ns": 207762064800655,
"end_wall_ns": 1783876189191227609,
"start_mono_ns": 207736941493919,
"start_wall_ns": 1783876164067921262
},
"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": 600,
"pass_rate": 0.17833333333333334,
"schema": 1,
"selection": {
"arrival_order_sha256": "50f1b34c344c451c6d7501290d0b53f147d0c0b6a4bc078b303d5c33576ebe2d",
"arrival_s": {
"distinct_n": 599,
"finite_n": 600,
"max": 59.90990000000002,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 600
},
"count": 600,
"long_gt4096": 187,
"offered_req_s": 10.0,
"offered_req_s_per_gpu": 2.5,
"raw_input_tokens": {
"distinct_n": 546,
"finite_n": 600,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 600
},
"raw_length_order_sha256": "08eff8eecd74dc4646aa45945bd752432ee5eb795006755527dd32d7178c1140",
"request_id_order_sha256": "21c1f3b7d972b19c952a894863a70d1e85bd0e24a7e7b6b0fcc088360d0e01bd"
},
"slo_pass_count": 107,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 184,
"finite_n": 184,
"max": 10.008890590608472,
"min": 4.802999944897281,
"missing_n": 416,
"n": 600
},
"ttft_ms": {
"distinct_n": 184,
"finite_n": 184,
"max": 5891.477338009281,
"min": 41.87891198671423,
"missing_n": 416,
"n": 600
}
}

View File

@@ -0,0 +1,22 @@
{
"accounting_mode": "graceful-footer",
"cell": "tp4_mns8",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 58725,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/opprof/opprof-v1-dp0-pid2762505-1783875811578126796.jsonl"
}

View File

@@ -0,0 +1,8 @@
SERVER taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/vllm serve /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B --host 127.0.0.1 --port 8707 --served-model-name qwen3-30b-a3b-community --max-num-batched-tokens 8192 --max-num-seqs 8 --tensor-parallel-size 4 --shutdown-timeout 120
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py warmup --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016591107009 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/warmup
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016591107009 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/anchor-0.016591107009
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016591107009 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/confirm-1-anchor-0.016591107009
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.016055910008 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/anchor-0.016055910008
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.017126304009 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/anchor-0.017126304009
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.017126304009 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/confirm-1-anchor-0.017126304009
CLIENT taskset -c 0-19,20-39,40-59,60-79 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/scripts/opprof_phase6_client.py run-anchor --study /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/provenance/study-tp4.json --cell tp4_mns8 --anchor 0.034252608017 --tp 4 --mns 8 --base-url http://127.0.0.1:8707 --result-dir /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/solo-authoritative/cells/tp4_mns8/anchor-0.034252608017

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.016591107009, "kind": "anchor", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.016591107009,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 308,
"feasible": true,
"interval": {
"elapsed_s": 60.446717466,
"end_mono_ns": 207530401973415,
"end_wall_ns": 1783875957528400301,
"start_mono_ns": 207469955255949,
"start_wall_ns": 1783875897081683055
},
"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": 308,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "860d2ac188790a401e93d3f99b9f37d6d69f0dfda1af94c37bc0067278444632",
"arrival_s": {
"distinct_n": 307,
"finite_n": 308,
"max": 59.75439999999999,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 308
},
"count": 308,
"long_gt4096": 96,
"offered_req_s": 5.133333333333334,
"offered_req_s_per_gpu": 1.2833333333333334,
"raw_input_tokens": {
"distinct_n": 288,
"finite_n": 308,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 308
},
"raw_length_order_sha256": "c533dffff00fdea5f5492826549ca09fa62fe46ef98942928115816f92a38771",
"request_id_order_sha256": "2407501cda53bf9c761c448dc50ab4780b4a55958cc00ba1b19cd09de1cf73e1"
},
"slo_pass_count": 308,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 308,
"finite_n": 308,
"max": 7.508626362165861,
"min": 3.4711365354262056,
"missing_n": 0,
"n": 308
},
"ttft_ms": {
"distinct_n": 308,
"finite_n": 308,
"max": 484.5911349984817,
"min": 35.676457977388054,
"missing_n": 0,
"n": 308
}
}

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.017126304009, "kind": "anchor", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.017126304009,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 317,
"feasible": true,
"interval": {
"elapsed_s": 60.494741705,
"end_mono_ns": 207730936466431,
"end_wall_ns": 1783876158062893709,
"start_mono_ns": 207670441724726,
"start_wall_ns": 1783876097568152371
},
"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": 317,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "37e0795a537a347b17e01cbe56e581172f28f709c8a9fc527cd2e149ef427a11",
"arrival_s": {
"distinct_n": 316,
"finite_n": 317,
"max": 59.75439999999999,
"min": 0.13000000000001818,
"missing_n": 0,
"n": 317
},
"count": 317,
"long_gt4096": 98,
"offered_req_s": 5.283333333333333,
"offered_req_s_per_gpu": 1.3208333333333333,
"raw_input_tokens": {
"distinct_n": 295,
"finite_n": 317,
"max": 8157.0,
"min": 69.0,
"missing_n": 0,
"n": 317
},
"raw_length_order_sha256": "4edec9417636579f3ebf9140d418b8072a89f80362751426a578737870179a9c",
"request_id_order_sha256": "93cd99ebf2a760cc440dce0cb7e51273686dcfbfb07650d27e9e16d2ff1d2eed"
},
"slo_pass_count": 317,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 317,
"finite_n": 317,
"max": 7.324393826727499,
"min": 3.5252888424791338,
"missing_n": 0,
"n": 317
},
"ttft_ms": {
"distinct_n": 317,
"finite_n": 317,
"max": 458.84576899698004,
"min": 35.29350899043493,
"missing_n": 0,
"n": 317
}
}

View File

@@ -0,0 +1 @@
{"schema":1,"record_type":"footer_checkpoint","stream":"opprof-v1-dp0-pid2762505-1783875811578126796.jsonl","encoded_records":58725,"written_records":58725,"dropped_records":0,"last_step_index":58724,"checkpoint_wall_ns":1783876193645775001,"flush_interval_seconds":1.0,"final":true}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1 @@
{"cell": "tp4_mns8", "anchor": 0.016591107009, "kind": "warmup", "pass_rate": 1.0, "feasible": true}

View File

@@ -0,0 +1,74 @@
{
"anchor": 0.016591107009,
"cell": "tp4_mns8",
"early_stop_reason": "",
"early_stopped": false,
"exact_output_count": 16,
"feasible": true,
"interval": {
"elapsed_s": 3.808491244,
"end_mono_ns": 207395951153778,
"end_wall_ns": 1783875823077580547,
"start_mono_ns": 207392142662534,
"start_wall_ns": 1783875819269089757
},
"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": "warmup",
"mns": 8,
"observed_count": 16,
"pass_rate": 1.0,
"schema": 1,
"selection": {
"arrival_order_sha256": "99f2dcf01a54ab81776395fdef964b2a109d37fd8d44f971f3723e99a012b35e",
"arrival_s": {
"distinct_n": 16,
"finite_n": 16,
"max": 3.0116999999999736,
"min": 0.0,
"missing_n": 0,
"n": 16
},
"count": 16,
"long_gt4096": 5,
"offered_req_s": 0.26666666666666666,
"offered_req_s_per_gpu": 0.06666666666666667,
"raw_input_tokens": {
"distinct_n": 16,
"finite_n": 16,
"max": 8150.0,
"min": 810.0,
"missing_n": 0,
"n": 16
},
"raw_length_order_sha256": "3b3e3258b82a4168ea8c3836458779878ca106893e1af47b23576e89de4b245f",
"request_id_order_sha256": "e321d81e19450f59c2ac022f6ae487ec4c72024453d015376c2df60b97167d76"
},
"slo_pass_count": 16,
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
"tp": 4,
"tpot_ms": {
"distinct_n": 16,
"finite_n": 16,
"max": 10.71806851977035,
"min": 5.432029015716444,
"missing_n": 0,
"n": 16
},
"ttft_ms": {
"distinct_n": 16,
"finite_n": 16,
"max": 360.8932939823717,
"min": 97.1808879985474,
"missing_n": 0,
"n": 16
}
}