[Benchmark] Remove re-exports from bench_serving.py (#19130)

benchmark/hicache/bench_long_context.py

@@ -12,7 +12,7 @@ from bench_multiturn import (
 )
 from tqdm.asyncio import tqdm
 
-from sglang.bench_serving import get_tokenizer
+from sglang.benchmark.utils import get_tokenizer
 
 
 class ContextWorkloadGenerator(WorkloadGenerator):

benchmark/hicache/bench_mix.py

@@ -12,12 +12,9 @@ from functools import wraps
 
 import aiohttp
 
-from sglang.bench_serving import (
-    RequestFuncOutput,
-    get_tokenizer,
-    remove_prefix,
-    sample_random_requests,
-)
+from sglang.bench_serving import RequestFuncOutput
+from sglang.benchmark.datasets import sample_random_requests
+from sglang.benchmark.utils import get_tokenizer, remove_prefix
 
 # Set up logger
 logger = logging.getLogger(__name__)

benchmark/hicache/bench_multiturn.py

@@ -11,7 +11,8 @@ import numpy as np
 import requests
 from tqdm.asyncio import tqdm
 
-from sglang.bench_serving import get_tokenizer, sample_random_requests
+from sglang.benchmark.datasets import sample_random_requests
+from sglang.benchmark.utils import get_tokenizer
 from sglang.test.kits.cache_hit_kit import async_request_sglang_generate, gen_payload
 
 

benchmark/hicache/bench_serving.py

@@ -32,7 +32,7 @@ from data_processing import MsgContent, SampleOutput, get_dataset
 from tqdm.asyncio import tqdm
 from transformers import PreTrainedTokenizerBase
 
-from sglang.bench_serving import get_tokenizer, remove_prefix, set_ulimit
+from sglang.benchmark.utils import get_tokenizer, remove_prefix, set_ulimit
 
 AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=20 * 60 * 60)
 

benchmark/hicache/data_processing.py

@@ -11,13 +11,13 @@ from nextqa import NExTQALoader
 from tqdm.asyncio import tqdm
 from transformers import PreTrainedTokenizerBase
 
-from sglang.bench_serving import (
+from sglang.benchmark.datasets import (
     SHAREGPT_FILENAME,
     SHAREGPT_REPO_ID,
-    download_and_cache_hf_file,
     gen_prompt,
     get_gen_prefix_cache_path,
 )
+from sglang.benchmark.utils import download_and_cache_hf_file
 from sglang.lang.chat_template import get_chat_template, get_chat_template_by_model_path
 from sglang.srt.entrypoints.openai.protocol import ChatCompletionMessageContentPart
 from sglang.utils import encode_video_base64

benchmark/lora/lora_bench.py

@@ -35,10 +35,9 @@ from sglang.bench_serving import (
     _create_bench_client_session,
     calculate_metrics,
     get_request,
-    get_tokenizer,
-    remove_prefix,
-    sample_random_requests,
 )
+from sglang.benchmark.datasets import sample_random_requests
+from sglang.benchmark.utils import get_tokenizer, remove_prefix
 
 global args