[Benchmark] Support ready check timeout in vllm bench serve (#21696)

Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
This commit is contained in:
Ye (Charlotte) Qi
2025-08-03 00:52:38 -07:00
committed by GitHub
co-authored by Roger Wang
parent 3dddbf1f25
commit 3f36c325fa
7 changed files with 94 additions and 11 deletions
+2 -2
View File
@@ -21,8 +21,8 @@ from vllm.benchmarks.datasets import (AIMODataset, BurstGPTDataset,
InstructCoderDataset, RandomDataset,
SampleRequest, ShareGPTDataset,
SonnetDataset, VisionArenaDataset)
from vllm.benchmarks.utils import (convert_to_pytorch_benchmark_format,
write_to_json)
from vllm.benchmarks.lib.utils import (convert_to_pytorch_benchmark_format,
write_to_json)
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
from vllm.entrypoints.openai.api_server import (
build_async_engine_client_from_engine_args)