GPU_COMMAND P09-capture-ON-server: taskset -c 0-19 /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 8200 --tensor-parallel-size 1 --enable-chunked-prefill --enable-prefix-caching --shutdown-timeout 120 --cudagraph-capture-sizes 1 2 3 4 5 6 7 8 9 16 24 32 40 48 56 64 72 80 88 96 104 112 120 128 136 144 152 160 168 176 184 192 200 208 216 224 232 240 248 256 272 288 304 320 336 352 368 384 400 416 432 448 464 480 496 512; expected=6-9m
GPU_COMMAND P09-capture-ON-client: taskset -c 0-19 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/scripts/opprof_phase3_client.py run --manifest /home/admin/cpfs/wjh/opprof-phase3-private/manifests/P09.jsonl --base-url http://127.0.0.1:8200 --model /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B --load-point moderate --saturation-result /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase3/primary/P09-C00/saturation/client/result.json --rate-fraction 0.60 --max-concurrency 256 --ignore-eos --temperature 0 --warmup-seconds 60 --clean-segment-seconds 80 --num-clean-segments 3 --recovery-seconds 30 --drain-timeout-seconds 120 --workload-seed 20260712 --server-seed 20260712 --result-dir /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase4-capture-p09/on/client; expected=5-7m
GPU_COMMAND P09-capture-OFF-server: taskset -c 0-19 /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 8200 --tensor-parallel-size 1 --enable-chunked-prefill --enable-prefix-caching --shutdown-timeout 120; expected=6-9m
GPU_COMMAND P09-capture-OFF-client: taskset -c 0-19 /tmp/wjh-opprof-phase2-dash0-20260711/.venv/bin/python /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/scripts/opprof_phase3_client.py run --manifest /home/admin/cpfs/wjh/opprof-phase3-private/manifests/P09.jsonl --base-url http://127.0.0.1:8200 --model /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B --load-point moderate --saturation-result /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase3/primary/P09-C00/saturation/client/result.json --rate-fraction 0.60 --max-concurrency 256 --ignore-eos --temperature 0 --warmup-seconds 60 --clean-segment-seconds 80 --num-clean-segments 3 --recovery-seconds 30 --drain-timeout-seconds 120 --workload-seed 20260712 --server-seed 20260712 --result-dir /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase4-capture-p09/off/client; expected=5-7m
{"delta": {"completed_throughput_relative": 0.0050675675675675436, "e2e_mean_latency_relative": -0.04096717785851722, "e2e_p95_latency_relative": 0.03011353223527924, "padding_fraction_points": -0.049797561163151524, "padding_reduction_fraction": 0.5827252753866776, "token_efficiency_relative": 0.0017943761453185214}, "gpu_hours_increment": 0.2963894498348236, "gpu_hours_total": 14.322264868590567, "off": {"arm": "OFF", "bucket_tokens": 237911, "capture_sizes": "default", "clean_completed": 1184, "clean_completed_throughput_rps": 4.933333333333334, "clean_failed": 0, "clean_offered_rps": 4.920833333333333, "drain_seconds": 0.7853007119847462, "e2e_latency_mean_s": 1.681152764688729, "e2e_latency_p95_s": 3.8763178953449815, "gpu_hours": 0.13751606033907995, "graph_hit_steps": 12252, "graph_miss_rate": 0.045199501246882795, "layer1_invariants": {"cudagraph_identity": true, "footer_balanced": true, "footer_written_matches": true, "schema_1": true, "sidecar_agrees": true, "sidecar_final": true, "steps_unique_contiguous": true, "token_composition": true, "zero_drops": true}, "layer1_records": 16491, "model_step_duration_ms": 479367.749483, "model_steps": 12832, "padding_fraction": 0.08545632610514016, "padding_tokens": 20331, "schema": 1, "token_efficiency_per_ms": 4.5540506267984115, "useful_tokens": 2183065}, "on": {"arm": "ON", "bucket_tokens": 227714, "capture_sizes": [1, 2, 3, 4, 5, 6, 7, 8, 9, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], "clean_completed": 1190, "clean_completed_throughput_rps": 4.958333333333333, "clean_failed": 0, "clean_offered_rps": 4.920833333333333, "drain_seconds": 0.7876331160077825, "e2e_latency_mean_s": 1.612280680370388, "e2e_latency_p95_s": 3.9930475192406423, "gpu_hours": 0.15887338949574364, "graph_hit_steps": 14253, "graph_miss_rate": 0.0389724226282786, "layer1_invariants": {"cudagraph_identity": true, "footer_balanced": true, "footer_written_matches": true, "schema_1": true, "sidecar_agrees": true, "sidecar_final": true, "steps_unique_contiguous": true, "token_composition": true, "zero_drops": true}, "layer1_records": 17579, "model_step_duration_ms": 478655.543996, "model_steps": 14831, "padding_fraction": 0.035658764941988635, "padding_tokens": 8120, "schema": 1, "token_efficiency_per_ms": 4.562222306607711, "useful_tokens": 2183733}, "plan": {"added_capture_sizes": [3, 5, 6, 7, 9], "clean_seconds": 240, "gpu": 0, "gpu_hour_limit": 16.0, "load": "moderate", "manifest": "/home/admin/cpfs/wjh/opprof-phase3-private/manifests/P09.jsonl", "measured_padding_recovery_bound": 0.049776380388728225, "on_capture_sizes": [1, 2, 3, 4, 5, 6, 7, 8, 9, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], "order": ["ON", "OFF"], "pattern": "P09", "primary_metric": "clean graph-hit padding_fraction", "prior_gpu_hours": 14.025875418755744, "profile": false, "projected_increment_gpu_hours": 0.5, "projected_total_gpu_hours": 14.525875418755744, "rate_fraction": 0.6, "saturation_result": "/home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase3/primary/P09-C00/saturation/client/result.json", "schema": 1, "secondary_metrics": ["Layer-1 useful scheduled tokens/model-step millisecond", "clean completed request throughput", "clean request latency"], "warmup_seconds": 60}, "schema": 1}