xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:24:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix the benchmark's README and improve the error messages for the benchmark's argument checks (#22654)

Browse Source 
Signed-off-by: tanruixiang <tanruixiang0104@gmail.com>
This commit is contained in:
Ruixiang Tan 2025-08-20 01:18:51 +08:00 committed by GitHub
parent d6a1a20973
commit 03d4235fd2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
benchmarks/README.md
View File

@ -194,6 +194,7 @@ vllm serve Qwen/Qwen2-VL-7B-Instruct
```bash ```bash
vllm bench serve \ vllm bench serve \
--backend openai-chat \ --backend openai-chat \
--endpoint-type openai-chat \
--model Qwen/Qwen2-VL-7B-Instruct \ --model Qwen/Qwen2-VL-7B-Instruct \
--endpoint /v1/chat/completions \ --endpoint /v1/chat/completions \
--dataset-name hf \ --dataset-name hf \
@ -230,6 +231,7 @@ vllm serve Qwen/Qwen2-VL-7B-Instruct
```bash ```bash
vllm bench serve \ vllm bench serve \
--backend openai-chat \ --backend openai-chat \
--endpoint-type openai-chat \
--model Qwen/Qwen2-VL-7B-Instruct \ --model Qwen/Qwen2-VL-7B-Instruct \
--endpoint /v1/chat/completions \ --endpoint /v1/chat/completions \
--dataset-name hf \ --dataset-name hf \
@ -244,6 +246,7 @@ vllm bench serve \
```bash ```bash
vllm bench serve \ vllm bench serve \
--backend openai-chat \ --backend openai-chat \
--endpoint-type openai-chat \
--model Qwen/Qwen2-VL-7B-Instruct \ --model Qwen/Qwen2-VL-7B-Instruct \
--endpoint /v1/chat/completions \ --endpoint /v1/chat/completions \
--dataset-name hf \ --dataset-name hf \

5
vllm/benchmarks/datasets.py
View File

@ -740,10 +740,11 @@ def get_samples(args, tokenizer) -> list[SampleRequest]:
"openai-chat", "openai-chat",
"openai-audio", "openai-audio",
]: ]:
# multi-modal benchmark is only available on OpenAI Chat backend. # multi-modal benchmark is only available on OpenAI Chat
# endpoint-type.
raise ValueError( raise ValueError(
"Multi-modal content is only supported on 'openai-chat' and " "Multi-modal content is only supported on 'openai-chat' and "
"'openai-audio' backend.") "'openai-audio' endpoint-type.")
input_requests = dataset_class( input_requests = dataset_class(
dataset_path=args.dataset_path, dataset_path=args.dataset_path,
dataset_subset=args.hf_subset, dataset_subset=args.hf_subset,