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:
66
runs/opprof-phase3/phase4/capture-p09/off/client-sanity.json
Normal file
66
runs/opprof-phase3/phase4/capture-p09/off/client-sanity.json
Normal file
@@ -0,0 +1,66 @@
|
||||
{
|
||||
"invariants": {
|
||||
"clean_duration_exact": true,
|
||||
"clean_failures_zero": true,
|
||||
"concurrency_bounded": true,
|
||||
"drain_within_timeout": true,
|
||||
"manifest_no_wrap": true,
|
||||
"manifest_not_exhausted": true,
|
||||
"moderate_offered_within_5pct": 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": 1477,
|
||||
"max": 64.0,
|
||||
"min": 64.0,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
},
|
||||
"admitted_s": {
|
||||
"distinct_n": 1477,
|
||||
"finite_n": 1477,
|
||||
"max": 299.8483776419889,
|
||||
"min": 0.00022695399820804596,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
},
|
||||
"completed_s": {
|
||||
"distinct_n": 1477,
|
||||
"finite_n": 1477,
|
||||
"max": 300.78334441498737,
|
||||
"min": 0.6682249770092312,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
},
|
||||
"input_tokens": {
|
||||
"distinct_n": 944,
|
||||
"finite_n": 1477,
|
||||
"max": 8161.0,
|
||||
"min": 128.0,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
},
|
||||
"requested_output_tokens": {
|
||||
"distinct_n": 1,
|
||||
"finite_n": 1477,
|
||||
"max": 64.0,
|
||||
"min": 64.0,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
},
|
||||
"scheduled_s": {
|
||||
"distinct_n": 1477,
|
||||
"finite_n": 1477,
|
||||
"max": 299.84763839512016,
|
||||
"min": 0.0,
|
||||
"missing_n": 0,
|
||||
"n": 1477
|
||||
}
|
||||
},
|
||||
"schema": 1
|
||||
}
|
||||
2
runs/opprof-phase3/phase4/capture-p09/off/commands.log
Normal file
2
runs/opprof-phase3/phase4/capture-p09/off/commands.log
Normal file
@@ -0,0 +1,2 @@
|
||||
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
|
||||
34
runs/opprof-phase3/phase4/capture-p09/off/summary.json
Normal file
34
runs/opprof-phase3/phase4/capture-p09/off/summary.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
Reference in New Issue
Block a user