[Bugfix] reasoning_parser parameter handling in run_batch.py (#26225)
Signed-off-by: inc-jeong <inc.jeong@navercorp.com> Signed-off-by: InChang Jeong <inc.jeong@navercorp.com> Co-authored-by: USER <user@AL02367916.local>
This commit is contained in:
@@ -31,6 +31,7 @@ from vllm.entrypoints.openai.serving_embedding import OpenAIServingEmbedding
|
||||
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
|
||||
from vllm.entrypoints.openai.serving_score import ServingScores
|
||||
from vllm.logger import init_logger
|
||||
from vllm.reasoning import ReasoningParserManager
|
||||
from vllm.utils import FlexibleArgumentParser, random_uuid
|
||||
from vllm.version import __version__ as VLLM_VERSION
|
||||
|
||||
@@ -331,6 +332,17 @@ async def run_request(
|
||||
return batch_output
|
||||
|
||||
|
||||
def validate_run_batch_args(args):
|
||||
valid_reasoning_parses = ReasoningParserManager.reasoning_parsers.keys()
|
||||
if (
|
||||
reasoning_parser := args.structured_outputs_config.reasoning_parser
|
||||
) and reasoning_parser not in valid_reasoning_parses:
|
||||
raise KeyError(
|
||||
f"invalid reasoning parser: {reasoning_parser} "
|
||||
f"(chose from {{ {','.join(valid_reasoning_parses)} }})"
|
||||
)
|
||||
|
||||
|
||||
async def run_batch(
|
||||
engine_client: EngineClient,
|
||||
args: Namespace,
|
||||
@@ -359,6 +371,7 @@ async def run_batch(
|
||||
base_model_paths=base_model_paths,
|
||||
lora_modules=None,
|
||||
)
|
||||
|
||||
openai_serving_chat = (
|
||||
OpenAIServingChat(
|
||||
engine_client,
|
||||
@@ -367,12 +380,14 @@ async def run_batch(
|
||||
request_logger=request_logger,
|
||||
chat_template=None,
|
||||
chat_template_content_format="auto",
|
||||
reasoning_parser=args.structured_outputs_config.reasoning_parser,
|
||||
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
|
||||
enable_force_include_usage=args.enable_force_include_usage,
|
||||
)
|
||||
if "generate" in supported_tasks
|
||||
else None
|
||||
)
|
||||
|
||||
openai_serving_embedding = (
|
||||
OpenAIServingEmbedding(
|
||||
engine_client,
|
||||
@@ -504,6 +519,8 @@ async def main(args: Namespace):
|
||||
from vllm.entrypoints.openai.api_server import build_async_engine_client
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
|
||||
validate_run_batch_args(args)
|
||||
|
||||
async with build_async_engine_client(
|
||||
args,
|
||||
usage_context=UsageContext.OPENAI_BATCH_RUNNER,
|
||||
|
||||
Reference in New Issue
Block a user