a4e38b9e33
Move all experiments under hardware-specific folders: - experiments/h200/ : H200 GPU experiments (15 dirs) - experiments/h20/ : H20 GPU experiments (2 dirs) - experiments/p800/ : Kunlun P800 experiments (3 dirs) - experiments/pro6000/ : RTX 6000D experiments (2 dirs) This improves discoverability and keeps hardware-specific configs isolated from each other.
168 lines
6.3 KiB
Python
Executable File
168 lines
6.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Parse H200 SGLang baseline benchmark JSONL outputs.
|
|
|
|
Reads the single-line summary JSON produced by
|
|
`sglang.bench_serving --output-file --output-details` and generates:
|
|
- results.json (appended scenarios)
|
|
- report.md (human-readable summary)
|
|
|
|
Usage:
|
|
python3 parse_results.py <result_root>
|
|
"""
|
|
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
def parse_jsonl(path: Path) -> dict | None:
|
|
"""Read the first (and usually only) JSON object from the JSONL file."""
|
|
with open(path, "r", encoding="utf-8") as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
try:
|
|
return json.loads(line)
|
|
except json.JSONDecodeError:
|
|
continue
|
|
return None
|
|
|
|
|
|
def compute_metrics(data: dict) -> dict:
|
|
completed = data.get("completed", 0)
|
|
total = len(data.get("input_lens", []))
|
|
failed = total - completed if total > 0 else 0
|
|
duration_s = data.get("duration", 0.0)
|
|
|
|
return {
|
|
"success": completed,
|
|
"failed": failed,
|
|
"duration_s": duration_s,
|
|
"request_throughput": data.get("request_throughput", 0.0),
|
|
"input_token_throughput": data.get("input_throughput", 0.0),
|
|
"output_token_throughput": data.get("output_throughput", 0.0),
|
|
"total_token_throughput": data.get("total_throughput", 0.0),
|
|
"total_input_tokens": data.get("total_input_tokens", 0),
|
|
"total_output_tokens": data.get("total_output_tokens", 0),
|
|
"e2e_ms": {
|
|
"mean": data.get("mean_e2e_latency_ms", 0.0),
|
|
"p50": data.get("median_e2e_latency_ms", 0.0),
|
|
"p90": data.get("p90_e2e_latency_ms", 0.0),
|
|
"p95": data.get("p95_e2e_latency_ms", 0.0),
|
|
"p99": data.get("p99_e2e_latency_ms", 0.0),
|
|
},
|
|
"ttft_ms": {
|
|
"mean": data.get("mean_ttft_ms", 0.0),
|
|
"p50": data.get("median_ttft_ms", 0.0),
|
|
"p90": data.get("p90_ttft_ms", 0.0),
|
|
"p95": data.get("p95_ttft_ms", 0.0),
|
|
"p99": data.get("p99_ttft_ms", 0.0),
|
|
},
|
|
"tpot_ms": {
|
|
"mean": data.get("mean_tpot_ms", 0.0),
|
|
"p50": data.get("median_tpot_ms", 0.0),
|
|
"p90": data.get("p90_tpot_ms", 0.0),
|
|
"p95": data.get("p95_tpot_ms", 0.0),
|
|
"p99": data.get("p99_tpot_ms", 0.0),
|
|
},
|
|
"itl_ms": {
|
|
"mean": data.get("mean_itl_ms", 0.0),
|
|
"p50": data.get("median_itl_ms", 0.0),
|
|
"p90": data.get("p90_itl_ms", 0.0),
|
|
"p95": data.get("p95_itl_ms", 0.0),
|
|
"p99": data.get("p99_itl_ms", 0.0),
|
|
},
|
|
}
|
|
|
|
|
|
def scenario_name(concurrency: int, input_len: int, output_len: int) -> str:
|
|
return f"c{concurrency}_i{input_len}_o{output_len}"
|
|
|
|
|
|
def append_scenario(results_json: Path, scenario: dict) -> None:
|
|
with open(results_json, "r", encoding="utf-8") as f:
|
|
data = json.load(f)
|
|
data["scenarios"].append(scenario)
|
|
with open(results_json, "w", encoding="utf-8") as f:
|
|
json.dump(data, f, indent=2, ensure_ascii=False)
|
|
|
|
|
|
def generate_report(result_root: Path, scenarios: list[dict]) -> None:
|
|
report_path = result_root / "report.md"
|
|
with open(report_path, "w", encoding="utf-8") as f:
|
|
f.write("# H200 SGLang Baseline Benchmark Report\n\n")
|
|
f.write(f"- Result root: `{result_root}`\n")
|
|
f.write("- Model: `/data/models/DeepSeek-V4-Flash`\n")
|
|
f.write("- Backend: SGLang (TP=8, moe-runner-backend=marlin, no speculative decoding)\n")
|
|
f.write("- Benchmark client: `sglang.bench_serving --backend sglang`\n\n")
|
|
|
|
f.write("## Results\n\n")
|
|
f.write("| Scenario | Concurrency | Input | Output | Duration(s) | Success | Req/s | In tok/s | Out tok/s | Total tok/s | Mean TTFT(ms) | P95 TTFT(ms) | P99 TTFT(ms) | Mean TPOT(ms) | P95 TPOT(ms) | P99 TPOT(ms) | Mean E2E(ms) | P95 E2E(ms) | P99 E2E(ms) |\n")
|
|
f.write("|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|\n")
|
|
|
|
for s in scenarios:
|
|
cfg = s["config"]
|
|
m = s["metrics"]
|
|
f.write(
|
|
f"| {s['name']} | {cfg['concurrency']} | {cfg['input_len']} | {cfg['output_len']} | "
|
|
f"{m['duration_s']:.2f} | {m['success']} | {m['request_throughput']:.2f} | "
|
|
f"{m['input_token_throughput']:.2f} | {m['output_token_throughput']:.2f} | "
|
|
f"{m['total_token_throughput']:.2f} | "
|
|
f"{m['ttft_ms']['mean']:.2f} | {m['ttft_ms']['p95']:.2f} | {m['ttft_ms']['p99']:.2f} | "
|
|
f"{m['tpot_ms']['mean']:.2f} | {m['tpot_ms']['p95']:.2f} | {m['tpot_ms']['p99']:.2f} | "
|
|
f"{m['e2e_ms']['mean']:.2f} | {m['e2e_ms']['p95']:.2f} | {m['e2e_ms']['p99']:.2f} |\n"
|
|
)
|
|
f.write("\n")
|
|
|
|
|
|
def main() -> None:
|
|
result_root = Path(sys.argv[1]) if len(sys.argv) > 1 else Path("results")
|
|
raw_dir = result_root / "raw_outputs"
|
|
results_json = result_root / "results.json"
|
|
|
|
if not raw_dir.exists():
|
|
raise SystemExit(f"raw_outputs directory not found: {raw_dir}")
|
|
|
|
scenarios = []
|
|
for jsonl_path in sorted(raw_dir.glob("sglang_*.jsonl")):
|
|
# Filename: sglang_MMDD_concurrency_inputlen_outputlen.jsonl
|
|
parts = jsonl_path.stem.split("_")
|
|
if len(parts) < 5:
|
|
continue
|
|
concurrency, input_len, output_len = int(parts[2]), int(parts[3]), int(parts[4])
|
|
|
|
data = parse_jsonl(jsonl_path)
|
|
if data is None:
|
|
continue
|
|
|
|
metrics = compute_metrics(data)
|
|
scenario = {
|
|
"name": scenario_name(concurrency, input_len, output_len),
|
|
"config": {
|
|
"concurrency": concurrency,
|
|
"input_len": input_len,
|
|
"output_len": output_len,
|
|
"dataset": "random",
|
|
"num_prompts": metrics["success"] + metrics["failed"],
|
|
},
|
|
"metrics": metrics,
|
|
"raw_file": str(jsonl_path),
|
|
}
|
|
scenarios.append(scenario)
|
|
|
|
if not scenarios:
|
|
print("No benchmark outputs found to parse")
|
|
return
|
|
|
|
if results_json.exists():
|
|
for s in scenarios:
|
|
append_scenario(results_json, s)
|
|
|
|
generate_report(result_root, scenarios)
|
|
print(f"Parsed {len(scenarios)} scenarios into {result_root}/report.md")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|