[misc] Move bench_serving into sglang.benchmark (sgl-project#28996)

Author: oleksii-tumanov

python/sglang/auto_benchmark_lib.py

@@ -1095,7 +1095,7 @@ def build_bench_command(
     command = [
         sys.executable,
         "-m",
-        "sglang.bench_serving",
+        "sglang.benchmark.serving",
         "--backend",
         backend,
         "--base-url",

python/sglang/bench_serving.py python/sglang/benchmark/serving.pypython/sglang/bench_serving.py renamed to python/sglang/benchmark/serving.py

@@ -18,7 +18,7 @@
 from types import SimpleNamespace
 from typing import Awaitable, Callable, NamedTuple, Optional
 
-from sglang.bench_serving import run_benchmark
+from sglang.benchmark.serving import run_benchmark
 from sglang.srt.utils import kill_process_tree
 from sglang.test.test_utils import (
     DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,

python/sglang/test/ascend/test_ascend_utils.py

@@ -67,7 +67,7 @@ def build_stress_test_command(
         command = [
             "python3",
             "-m",
-            "sglang.bench_serving",
+            "sglang.benchmark.serving",
             "--backend",
             "sglang-oai",
             "--base-url",

python/sglang/test/ci/ci_stress_utils.py

@@ -5,8 +5,8 @@
 import aiohttp
 import requests
 
-from sglang.bench_serving import RequestFuncOutput
 from sglang.benchmark.datasets.random import sample_random_requests
+from sglang.benchmark.serving import RequestFuncOutput
 from sglang.benchmark.utils import get_tokenizer, remove_prefix
 
 AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=20 * 60 * 60)

python/sglang/test/kits/cache_hit_kit.py

@@ -5,7 +5,7 @@
 from dataclasses import dataclass
 from typing import Any, Sequence
 
-from sglang.bench_serving import run_benchmark
+from sglang.benchmark.serving import run_benchmark
 from sglang.srt.utils import kill_process_tree
 from sglang.test.test_utils import (
     DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,

python/sglang/test/mock_model/utils.py

@@ -31,7 +31,7 @@
 import torch.nn.functional as F
 from PIL import Image
 
-from sglang.bench_serving import run_benchmark
+from sglang.benchmark.serving import run_benchmark
 from sglang.global_config import global_config
 from sglang.srt.environ import envs
 from sglang.srt.utils import (

python/sglang/test/test_utils.py

@@ -22,7 +22,7 @@
 
 from sglang.bench_one_batch_server import BenchArgs as OneBatchBenchArgs
 from sglang.bench_one_batch_server import run_benchmark as run_one_batch_benchmark
-from sglang.bench_serving import run_benchmark as run_serving_benchmark
+from sglang.benchmark.serving import run_benchmark as run_serving_benchmark
 from sglang.srt.server_args import ServerArgs
 from sglang.srt.utils import kill_process_tree
 from sglang.test.test_utils import (

test/manual/dsv4/test_dsv4_pro_mtp.py

@@ -6,7 +6,7 @@
 from http.server import BaseHTTPRequestHandler, HTTPServer
 from pathlib import Path
 
-from sglang.bench_serving import run_benchmark
+from sglang.benchmark.serving import run_benchmark
 from sglang.benchmark.utils import parse_custom_headers
 from sglang.srt.constants import HEALTH_CHECK_RID_PREFIX
 from sglang.srt.utils import kill_process_tree

test/registered/bench_fn/test_bench_serving_functionality.py

@@ -16,7 +16,7 @@
 from argparse import Namespace
 from http.server import BaseHTTPRequestHandler, HTTPServer
 
-from sglang.bench_serving import (
+from sglang.benchmark.serving import (
     RequestFuncInput,
     async_request_openai_chat_completions,
     calculate_metrics,