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>

runs/opprof-phase6/phase6/cells/tp2_mns32/warmup/result.json

@@ -0,0 +1,74 @@
+{
+  "anchor": 0.75390625,
+  "cell": "tp2_mns32",
+  "early_stop_reason": "",
+  "early_stopped": false,
+  "exact_output_count": 16,
+  "feasible": false,
+  "interval": {
+    "elapsed_s": 7.481165294,
+    "end_mono_ns": 201114243480033,
+    "end_wall_ns": 1783869541369906988,
+    "start_mono_ns": 201106762314739,
+    "start_wall_ns": 1783869533888742060
+  },
+  "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": 32,
+  "observed_count": 16,
+  "pass_rate": 0.75,
+  "schema": 1,
+  "selection": {
+    "arrival_order_sha256": "440dc3774dd5b89ed800eee12e44a20f62b0ee9b66094d8e05fa343fb2ba3dd7",
+    "arrival_s": {
+      "distinct_n": 16,
+      "finite_n": 16,
+      "max": 2.4043000000000125,
+      "min": 0.0,
+      "missing_n": 0,
+      "n": 16
+    },
+    "count": 16,
+    "long_gt4096": 5,
+    "offered_req_s": 0.26666666666666666,
+    "offered_req_s_per_gpu": 0.13333333333333333,
+    "raw_input_tokens": {
+      "distinct_n": 16,
+      "finite_n": 16,
+      "max": 7233.0,
+      "min": 71.0,
+      "missing_n": 0,
+      "n": 16
+    },
+    "raw_length_order_sha256": "cb99e1339d84161d25fbc6a3c6ed983f34c0276e7712a62c176a8b92b8cb7b93",
+    "request_id_order_sha256": "9d18ed5ddc01d283277e84d107b444833f6ab2838675a8c7ffaedb7a0c1d50cf"
+  },
+  "slo_pass_count": 12,
+  "study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
+  "tp": 2,
+  "tpot_ms": {
+    "distinct_n": 16,
+    "finite_n": 16,
+    "max": 48.713730740283914,
+    "min": 9.619937283601098,
+    "missing_n": 0,
+    "n": 16
+  },
+  "ttft_ms": {
+    "distinct_n": 16,
+    "finite_n": 16,
+    "max": 3962.258840998402,
+    "min": 814.5189289934933,
+    "missing_n": 0,
+    "n": 16
+  }
+}