[Docs] Add comprehensive CLI reference for all large vllm subcommands (#22601)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -24,8 +24,6 @@ from vllm.benchmarks.datasets import (AIMODataset, BurstGPTDataset,
|
||||
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)
|
||||
from vllm.inputs import TextPrompt, TokensPrompt
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.outputs import RequestOutput
|
||||
@@ -146,6 +144,8 @@ async def run_vllm_async(
|
||||
disable_detokenize: bool = False,
|
||||
) -> float:
|
||||
from vllm import SamplingParams
|
||||
from vllm.entrypoints.openai.api_server import (
|
||||
build_async_engine_client_from_engine_args)
|
||||
|
||||
async with build_async_engine_client_from_engine_args(
|
||||
engine_args,
|
||||
|
||||
Reference in New Issue
Block a user