feat: add deterministic CPU/GPU benchmark runner slice

packages/node/meshnet_node/performance_contract.py

@@ -1,8 +1,11 @@
-"""Versioned performance contract metadata for DGR-001.
+"""Versioned performance contract metadata and stub benchmark runner for DGR-001.
 
-This module intentionally captures the *contract* first: the model family,
-architecture alignment, benchmark lanes, and stop condition that later benchmark
-runs must satisfy. It does not download or execute a model.
+This module captures the *contract* first: the model family, architecture
+alignment, benchmark lanes, and stop condition that benchmark runs must
+satisfy. It also runs the contract's lanes through a deterministic stub
+backend so the report data shape exists end to end. It never downloads or
+executes a model; real transformers / llama.cpp backends plug in behind the
+same ``run()`` seam later.
 """
 
 from __future__ import annotations
@@ -174,13 +177,177 @@ def build_default_contract() -> PerformanceContract:
     return DEFAULT_CONTRACT
 
 
+BENCHMARK_SCHEMA_VERSION = 1
+STUB_OUTPUT_TOKENS = ("mesh", "activation", "seam", "baseline")
+# DeepSeek-V2-Lite is ~15.7B params at 2 bytes each; metadata only, nothing downloaded.
+_SAFETENSORS_BF16_ARTIFACT_GB = 31.4
+
+
+@dataclass(frozen=True)
+class LaneSample:
+    """Raw single-stream measurements one backend produces for a lane."""
+
+    ttft_ms: float
+    prefill_tok_per_sec: float
+    decode_tok_per_sec: float
+    rss_bytes: int
+    vram_bytes: int
+    artifact_bytes: int
+    output_tokens: tuple[str, ...]
+    failure_count: int = 0
+
+
+def _gb(value: float) -> int:
+    return int(value * 1024**3)
+
+
+class StubLaneBackend:
+    """Deterministic placeholder measurements until real lane execution lands.
+
+    The numbers are synthetic but directionally shaped — the Q2_K GGUF loads a
+    far smaller artifact and decodes faster than BF16 safetensors — so the
+    comparison and stop-condition plumbing can be exercised in CI.
+    """
+
+    source = "stub-backend"
+
+    # (runtime, device) -> (ttft_ms, prefill tok/s, decode tok/s, rss GB, vram GB)
+    _PROFILES = {
+        ("transformers", "cpu"): (1800.0, 45.0, 6.0, 33.0, 0.0),
+        ("llama.cpp", "cpu"): (950.0, 90.0, 14.0, 7.1, 0.0),
+        ("transformers", "gpu"): (420.0, 850.0, 34.0, 4.0, 33.0),
+        ("llama.cpp", "gpu"): (260.0, 640.0, 52.0, 1.5, 7.5),
+    }
+
+    def __init__(self, contract: PerformanceContract) -> None:
+        self._contract = contract
+
+    def run(self, lane: BenchmarkLane) -> LaneSample:
+        ttft_ms, prefill, decode, rss_gb, vram_gb = self._PROFILES[(lane.runtime, lane.device)]
+        artifact_gb = (
+            self._contract.model_target.gguf_size_gb
+            if lane.runtime == "llama.cpp"
+            else _SAFETENSORS_BF16_ARTIFACT_GB
+        )
+        return LaneSample(
+            ttft_ms=ttft_ms,
+            prefill_tok_per_sec=prefill,
+            decode_tok_per_sec=decode,
+            rss_bytes=_gb(rss_gb),
+            vram_bytes=_gb(vram_gb),
+            artifact_bytes=_gb(artifact_gb),
+            output_tokens=STUB_OUTPUT_TOKENS,
+        )
+
+
+def _output_drift(tokens: tuple[str, ...], reference: tuple[str, ...]) -> float:
+    """Fraction of positions where a lane's output diverges from its reference."""
+    length = max(len(tokens), len(reference))
+    if length == 0:
+        return 0.0
+    mismatches = sum(a != b for a, b in zip(tokens, reference)) + abs(len(tokens) - len(reference))
+    return round(mismatches / length, 4)
+
+
+def _metrics_for(sample: LaneSample, concurrency: int, output_drift: float) -> dict:
+    # Stub concurrency model: batching scales throughput at 85% efficiency and
+    # stretches per-request token latency and TTFT accordingly.
+    efficiency = 1.0 if concurrency == 1 else 0.85
+    p50_latency_ms = round(1000.0 / (sample.decode_tok_per_sec * efficiency), 4)
+    return {
+        "ttft_ms": round(sample.ttft_ms * (1 + 0.1 * (concurrency - 1)), 4),
+        "prefill_tok_per_sec": round(sample.prefill_tok_per_sec * efficiency, 4),
+        "decode_tok_per_sec": round(sample.decode_tok_per_sec * efficiency, 4),
+        "p50_latency_ms": p50_latency_ms,
+        "p95_latency_ms": round(p50_latency_ms * 1.25, 4),
+        "aggregate_throughput_tok_per_sec": round(sample.decode_tok_per_sec * concurrency * efficiency, 4),
+        "rss_bytes": sample.rss_bytes,
+        "vram_bytes": sample.vram_bytes,
+        "artifact_bytes": sample.artifact_bytes,
+        "failure_count": sample.failure_count,
+        "output_drift": output_drift,
+    }
+
+
+def _compare_device(lanes: list[tuple[BenchmarkLane, LaneSample]], device: str) -> dict:
+    by_runtime = {lane.runtime: (lane, sample) for lane, sample in lanes if lane.device == device}
+    safetensors_lane, safetensors = by_runtime["transformers"]
+    gguf_lane, gguf = by_runtime["llama.cpp"]
+    memory_metric = "vram_bytes" if device == "gpu" else "rss_bytes"
+    decode_speedup = round(gguf.decode_tok_per_sec / safetensors.decode_tok_per_sec, 4)
+    artifact_bytes_ratio = round(gguf.artifact_bytes / max(1, safetensors.artifact_bytes), 4)
+    return {
+        "safetensors_lane": safetensors_lane.id,
+        "gguf_lane": gguf_lane.id,
+        "decode_speedup": decode_speedup,
+        "ttft_speedup": round(safetensors.ttft_ms / max(0.001, gguf.ttft_ms), 4),
+        "artifact_bytes_ratio": artifact_bytes_ratio,
+        "memory_metric": memory_metric,
+        "memory_bytes_ratio": round(
+            getattr(gguf, memory_metric) / max(1, getattr(safetensors, memory_metric)), 4
+        ),
+        "output_drift": _output_drift(gguf.output_tokens, safetensors.output_tokens),
+        "gguf_benefit": decode_speedup >= 1.10 or artifact_bytes_ratio <= 0.5,
+    }
+
+
+def run_performance_benchmark(
+    contract: PerformanceContract = DEFAULT_CONTRACT,
+    backend: StubLaneBackend | None = None,
+) -> dict:
+    """Run every contract lane through a backend and compare GGUF to safetensors."""
+    backend = backend if backend is not None else StubLaneBackend(contract)
+    lanes = [(lane, backend.run(lane)) for lane in contract.benchmark_lanes]
+    references = {
+        lane.device: sample.output_tokens for lane, sample in lanes if lane.runtime == "transformers"
+    }
+    lane_reports = []
+    for lane, sample in lanes:
+        drift = _output_drift(sample.output_tokens, references.get(lane.device, sample.output_tokens))
+        lane_reports.append({
+            **lane.to_dict(),
+            "output_tokens": list(sample.output_tokens),
+            "results": [
+                {"concurrency": level, "metrics": _metrics_for(sample, level, drift)}
+                for level in lane.concurrency_levels
+            ],
+        })
+    devices = sorted({lane.device for lane, _ in lanes})
+    comparisons = {device: _compare_device(lanes, device) for device in devices}
+    gguf_benefit = any(comparison["gguf_benefit"] for comparison in comparisons.values())
+    return {
+        "schema_version": BENCHMARK_SCHEMA_VERSION,
+        "story_id": contract.story_id,
+        "source": getattr(backend, "source", "custom-backend"),
+        "model_target": contract.model_target.to_dict(),
+        "lanes": lane_reports,
+        "comparisons": comparisons,
+        "stop_condition": {
+            "text": contract.stop_condition,
+            "gguf_benefit": gguf_benefit,
+            "triggered": not gguf_benefit,
+        },
+    }
+
+
 def main(argv: list[str] | None = None) -> int:
     parser = argparse.ArgumentParser(description="Write the DGR-001 performance contract JSON")
     parser.add_argument("--json-out", type=Path, default=DEFAULT_OUTPUT_PATH, help="output JSON path")
+    parser.add_argument(
+        "--benchmark-out",
+        type=Path,
+        default=None,
+        help="also run the deterministic stub benchmark and write its JSON report here",
+    )
     args = parser.parse_args(argv)
     contract = build_default_contract()
     path = contract.write_json(args.json_out)
     print(path)
+    if args.benchmark_out is not None:
+        report = run_performance_benchmark(contract)
+        args.benchmark_out.parent.mkdir(parents=True, exist_ok=True)
+        args.benchmark_out.write_text(json.dumps(report, indent=2, sort_keys=True) + "\n", encoding="utf-8")
+        print(args.benchmark_out)
     return 0