[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:
co-authored by
Roger Wang
parent
3dddbf1f25
commit
3f36c325fa
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user