Profile additional Qualcomm model components

benchmarks/edge_harness/experiments/audit_qwen_tts_talker_qualcomm.py

@@ -6,6 +6,8 @@ from __future__ import annotations
 import argparse
 import hashlib
 import json
+import math
+from collections import Counter
 from pathlib import Path
 
 import numpy as np
@@ -61,6 +63,7 @@ def main() -> None:
     parser.add_argument("--output-report", type=Path, required=True)
     parser.add_argument("--expected-compile-options", default=COMPILE_OPTIONS)
     parser.add_argument("--expected-run-options", default="--compute_unit npu")
+    parser.add_argument("--profile-report", type=Path)
     args = parser.parse_args()
 
     compiled = json.loads(args.compile_report.read_text(encoding="utf-8"))
@@ -143,10 +146,39 @@ def main() -> None:
         "limits": [
             "The historical source export does not attest an exact checkpoint revision.",
             "The fixture is synthetic and has no token-to-audio quality tolerance.",
-            "Requested compute unit is not actual placement without a device profile.",
             "No predictor, vocoder, persistent cache loop or complete TTS stream was tested.",
         ],
     }
+    if args.profile_report is not None:
+        profiled = json.loads(args.profile_report.read_text(encoding="utf-8"))
+        if (profiled.get("status") != "SUCCESS"
+                or profiled.get("model_id") != compiled["target_model_id"]
+                or profiled.get("device") != inferred["device"]
+                or profiled.get("options") != args.expected_run_options):
+            raise ValueError("profile did not execute the same target, device and route")
+        summary = profiled["profile"]["execution_summary"]
+        samples = summary["all_inference_times"]
+        if not samples or any(not isinstance(value, int) or value <= 0 for value in samples):
+            raise ValueError("profile has no valid inference samples")
+        units = Counter(row.get("compute_unit") for row in profiled["profile"]["execution_detail"])
+        if not units:
+            raise ValueError("profile has no compute-unit detail")
+        ordered = sorted(samples)
+        report["profile"] = {
+            "job_id": profiled["job_id"],
+            "sample_count": len(samples),
+            "sample_min_us": ordered[0],
+            "nearest_rank_p50_us": ordered[math.ceil(0.50 * len(samples)) - 1],
+            "nearest_rank_p95_us": ordered[math.ceil(0.95 * len(samples)) - 1],
+            "reported_estimated_inference_time_us": summary["estimated_inference_time"],
+            "reported_peak_memory_bytes": summary["estimated_inference_peak_memory"],
+            "reported_first_load_time_us": summary["first_load_time"],
+            "reported_first_load_peak_memory_bytes": summary["first_load_peak_memory"],
+            "compute_unit_row_counts": dict(units),
+        }
+        report["status"] = "component_inference_numeric_and_placement_measured"
+    else:
+        report["limits"].append("Requested compute unit is not actual placement without a device profile.")
     args.output_report.write_text(json.dumps(report, indent=2) + "\n", encoding="utf-8")
     print(json.dumps({
         "status": report["status"],

benchmarks/edge_harness/experiments/probe_internvla_hosted_latent_actions.py

@@ -29,6 +29,7 @@ def main() -> None:
     parser = argparse.ArgumentParser(description=__doc__)
     for name in ("model-dir", "cosmos-dir", "processor-dir", "fixture", "device-output", "audit-report", "output"):
         parser.add_argument(f"--{name}", type=Path, required=True)
+    parser.add_argument("--device-name", default="Samsung Galaxy S25")
     args = parser.parse_args()
 
     os.environ["INTERNVLA_A1_COSMOS_DIR"] = str(args.cosmos_dir.resolve(strict=True))
@@ -48,10 +49,13 @@ def main() -> None:
     if sha256(checkpoint) != CHECKPOINT_SHA256 or sha256(args.fixture) != FIXTURE_SHA256:
         raise ValueError("checkpoint or encoder fixture differs from pinned source")
     audit = json.loads(args.audit_report.read_text(encoding="utf-8"))
-    if (audit.get("status") != "component_inference_numeric_measured"
-            or audit.get("device", {}).get("name") != "Samsung Galaxy S25"
+    if (audit.get("status") not in {
+                "component_inference_numeric_measured",
+                "component_inference_numeric_and_placement_measured",
+            }
+            or audit.get("device", {}).get("name") != args.device_name
             or audit.get("files", {}).get("device_output", {}).get("sha256") != sha256(args.device_output)):
-        raise ValueError("hosted latent lacks audited S25 provenance")
+        raise ValueError(f"hosted latent lacks audited {args.device_name} provenance")
     with np.load(args.fixture, allow_pickle=False) as fixture:
         source_latent = np.asarray(fixture["pattern_reference"])
     with np.load(args.device_output, allow_pickle=False) as output:
@@ -130,8 +134,9 @@ def main() -> None:
     hosted = hosted_actions.astype(np.float64).ravel()
     delta = source - hosted
     report = {
-        "scope": "S25 hosted Cosmos latent injected into local CPU InternVLA policy with synthetic state/noise; no device-local policy or robot-task result",
+        "scope": f"{args.device_name} hosted Cosmos latent injected into local CPU InternVLA policy with synthetic state/noise; no device-local policy or robot-task result",
         "status": "synthetic_action_sensitivity_measured",
+        "hosted_device_name": args.device_name,
         "policy_checkpoint_sha256": CHECKPOINT_SHA256,
         "fixture_sha256": FIXTURE_SHA256,
         "hosted_output_sha256": sha256(args.device_output),