Skip to content

[Benchmark][Doc] Update throughput benchmark and README #15998

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 4 commits into from
Apr 4, 2025
Merged

[Benchmark][Doc] Update throughput benchmark and README #15998

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e3871ec
[Benchmark] Update readme and throughput benchmark
StevenShi-23 Apr 3, 2025
a800045
add aimo dataset split
StevenShi-23 Apr 3, 2025
e0dc790
[Benchmark] Explicit set hf dataset subset for AIMO
StevenShi-23 Apr 4, 2025
143ab6a
small refactor
ywang96 Apr 4, 2025
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
29 changes: 29 additions & 0 deletions benchmarks/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,12 @@ become available.
<td style="text-align: center;">✅</td>
<td style="text-align: center;">✅</td>
<td><code>likaixin/InstructCoder</code></td>
</tr>
<tr>
<td><strong>HuggingFace-AIMO</strong></td>
<td style="text-align: center;">✅</td>
<td style="text-align: center;">✅</td>
<td><code>AI-MO/aimo-validation-aime</code> , <code>AI-MO/NuminaMath-1.5</code>, <code>AI-MO/NuminaMath-CoT</code></td>
</tr>
<tr>
<td><strong>HuggingFace-Other</strong></td>
Expand Down Expand Up @@ -187,6 +193,17 @@ python3 vllm/benchmarks/benchmark_serving.py \
--num-prompts 10
```

**`AI-MO/aimo-validation-aime`**

``` bash
python3 vllm/benchmarks/benchmark_serving.py \
--model Qwen/QwQ-32B \
--dataset-name hf \
--dataset-path AI-MO/aimo-validation-aime \
--num-prompts 10 \
--seed 42
```

---
## Example - Offline Throughput Benchmark

Expand Down Expand Up @@ -278,6 +295,18 @@ python3 vllm/benchmarks/benchmark_throughput.py \
--num-prompts 10
```

**`AI-MO/aimo-validation-aime`**

```bash
python3 benchmarks/benchmark_throughput.py \
--model Qwen/QwQ-32B \
--backend vllm \
--dataset-name hf \
--dataset-path AI-MO/aimo-validation-aime \
--hf-split train \
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you can remove this line --hf-split train \

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

--num-prompts 10
```

### Benchmark with LoRA Adapters

``` bash
Expand Down
26 changes: 15 additions & 11 deletions benchmarks/benchmark_throughput.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,10 @@

import torch
import uvloop
from benchmark_dataset import (BurstGPTDataset, ConversationDataset,
InstructCoderDataset, RandomDataset,
SampleRequest, ShareGPTDataset, SonnetDataset,
VisionArenaDataset)
from benchmark_dataset import (AIMODataset, BurstGPTDataset,
ConversationDataset, InstructCoderDataset,
RandomDataset, SampleRequest, ShareGPTDataset,
SonnetDataset, VisionArenaDataset)
from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
from tqdm import tqdm
from transformers import (AutoModelForCausalLM, AutoTokenizer,
Expand Down Expand Up @@ -332,7 +332,10 @@ def get_requests(args, tokenizer):
common_kwargs['dataset_subset'] = args.hf_subset
common_kwargs['dataset_split'] = args.hf_split
sample_kwargs["enable_multimodal_chat"] = True

elif args.dataset_path in AIMODataset.SUPPORTED_DATASET_PATHS:
dataset_cls = AIMODataset
common_kwargs['dataset_subset'] = None
common_kwargs['dataset_split'] = "train"
else:
raise ValueError(f"Unknown dataset name: {args.dataset_name}")
# Remove None values
Expand Down Expand Up @@ -467,12 +470,13 @@ def validate_args(args):
since --dataset-name is not 'hf'.",
stacklevel=2)
elif args.dataset_name == "hf":
if args.dataset_path in VisionArenaDataset.SUPPORTED_DATASET_PATHS:
assert args.backend == "vllm-chat", "VisionArenaDataset needs to use vllm-chat as the backend." #noqa: E501
elif args.dataset_path in InstructCoderDataset.SUPPORTED_DATASET_PATHS:
assert args.backend == "vllm", "InstructCoder dataset needs to use vllm as the backend." #noqa: E501
elif args.dataset_path in ConversationDataset.SUPPORTED_DATASET_PATHS:
assert args.backend == "vllm-chat", "ConversationDataset needs to use vllm-chat as the backend." #noqa: E501
if args.dataset_path in (
VisionArenaDataset.SUPPORTED_DATASET_PATHS.keys()
| ConversationDataset.SUPPORTED_DATASET_PATHS):
assert args.backend == "vllm-chat", f"{args.dataset_path} needs to use vllm-chat as the backend." #noqa: E501
elif args.dataset_path in (InstructCoderDataset.SUPPORTED_DATASET_PATHS
| AIMODataset.SUPPORTED_DATASET_PATHS):
assert args.backend == "vllm", f"{args.dataset_path} needs to use vllm as the backend." #noqa: E501
else:
raise ValueError(
f"{args.dataset_path} is not supported by hf dataset.")
Expand Down