biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][Doc] Fully deprecate old bench scripts for serving / throughput / latency (#24411)

Browse Source 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
This commit is contained in:
Ye (Charlotte) Qi
2025-09-09 03:02:35 -07:00
committed by GitHub
parent 3d2a2de8f7
commit 6fb2788163
4 changed files with 41 additions and 2246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/README.md
View File

@@ -694,7 +694,7 @@ python -m vllm.entrypoints.openai.api_server \
Send requests with images:
```bash
python benchmarks/benchmark_serving.py \
vllm bench serve \
--backend openai-chat \
--model Qwen/Qwen2.5-VL-7B-Instruct \
--dataset-name sharegpt \
@@ -721,7 +721,7 @@ python -m vllm.entrypoints.openai.api_server \
Send requests with videos:
```bash
python benchmarks/benchmark_serving.py \
vllm bench serve \
--backend openai-chat \
--model Qwen/Qwen2.5-VL-7B-Instruct \
--dataset-name sharegpt \