Skip to content

feat: Make benchmark_serving part of the library #5428

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 25, 2025
Merged

feat: Make benchmark_serving part of the library #5428

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Empty file added tensorrt_llm/serve/scripts/__init__.py
View file
Open in desktop
Empty file.
3 changes: 2 additions & 1 deletion tensorrt_llm/serve/scripts/benchmark_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,10 +26,11 @@

import numpy as np
import pandas as pd
from benchmark_utils import download_and_cache_file
from datasets import load_dataset
from transformers import PreTrainedTokenizerBase

from .benchmark_utils import download_and_cache_file

logger = logging.getLogger(__name__)

# -----------------------------------------------------------------------------
Expand Down
19 changes: 10 additions & 9 deletions tensorrt_llm/serve/scripts/benchmark_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,18 +31,19 @@
from typing import Any, Optional

import numpy as np
from backend_request_func import (ASYNC_REQUEST_FUNCS,
OPENAI_COMPATIBLE_BACKENDS, RequestFuncInput,
RequestFuncOutput, get_tokenizer)
from benchmark_dataset import (AIMODataset, BurstGPTDataset,
ConversationDataset, HuggingFaceDataset,
InstructCoderDataset, RandomDataset,
SampleRequest, ShareGPTDataset, SonnetDataset,
VisionArenaDataset)
from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
from tqdm.asyncio import tqdm
from transformers import PreTrainedTokenizerBase

from .backend_request_func import (ASYNC_REQUEST_FUNCS,
OPENAI_COMPATIBLE_BACKENDS, RequestFuncInput,
RequestFuncOutput, get_tokenizer)
from .benchmark_dataset import (AIMODataset, BurstGPTDataset,
ConversationDataset, HuggingFaceDataset,
InstructCoderDataset, RandomDataset,
SampleRequest, ShareGPTDataset, SonnetDataset,
VisionArenaDataset)
from .benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json

MILLISECONDS_TO_SECONDS_CONVERSION = 1000


Expand Down