[Frontend] Consolidate scale out entrypoints (#44512)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-06-29 03:18:53 -07:00
committed by GitHub
parent eddfd4cf21
commit 3483240b7e
45 changed files with 422 additions and 289 deletions
-15
View File
@@ -66,7 +66,6 @@ async def init_generate_state(
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
from vllm.entrypoints.serve.disagg.serving import ServingTokens
from vllm.entrypoints.serve.utils.fingerprint import set_default_fingerprint_mode
# Applied before any serving class is constructed so that each one picks
@@ -175,20 +174,6 @@ async def init_generate_state(
if "generate" in supported_tasks
else None
)
state.serving_tokens = (
ServingTokens(
engine_client,
state.openai_serving_models,
state.online_renderer,
request_logger=request_logger,
return_tokens_as_token_ids=args.return_tokens_as_token_ids,
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
enable_log_outputs=args.enable_log_outputs,
force_no_detokenize=args.tokens_only,
)
if "generate" in supported_tasks
else None
)
from .generative_scoring.serving import ServingGenerativeScoring