rebase: align vllm-omni with vLLM 2dfaae752b4d

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-07-11 14:21:14 +08:00
1 parent 4063db33ff
commit 7dcbe4e957
7 files changed
+70 -31

No files matched your search

+10 -11
View File
@@ -60,12 +60,11 @@ from vllm.entrypoints.pooling.classify.serving import ServingClassification
from vllm.entrypoints.pooling.embed.serving import ServingEmbedding as OpenAIServingEmbedding
from vllm.entrypoints.pooling.pooling.serving import ServingPooling
from vllm.entrypoints.pooling.scoring.serving import ServingScores
from vllm.entrypoints.serve.disagg.serving import ServingTokens
from vllm.entrypoints.scale_out.token_in_token_out.serving import ServingTokens
# vLLM moved `base` from openai.basic.api_router to serve.instrumentator.basic.
# Keep a fallback for older/newer upstream layouts during rebase windows.
from vllm.entrypoints.serve.instrumentator.basic import base
from vllm.entrypoints.serve.render.serving import OpenAIServingRender
from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
@@ -85,6 +84,7 @@ from vllm.entrypoints.speech_to_text.translation.serving import (
OpenAIServingTranslation,
)
from vllm.logger import init_logger
from vllm.renderers.online_renderer import OnlineRenderer
from vllm.tasks import POOLING_TASKS
from vllm.tool_parsers import ToolParserManager
from vllm.utils import random_uuid
@@ -895,11 +895,10 @@ async def omni_init_app_state(
await state.openai_serving_models.init_static_loras()
# NOTE: kept aligned with upstream `init_app_state`:
# Use OpenAIServingRender (replaces the old OnlineRenderer + OnlineDerenderer + ServingRender split).
state.openai_serving_render = OpenAIServingRender(
# Use OnlineRenderer (replaced OpenAIServingRender which was removed upstream).
state.online_renderer = OnlineRenderer(
model_config=engine_client.model_config,
renderer=engine_client.renderer,
model_registry=state.openai_serving_models.registry,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
@@ -916,7 +915,7 @@ async def omni_init_app_state(
OpenAIServingResponses(
engine_client,
state.openai_serving_models,
openai_serving_render=state.openai_serving_render,
state.online_renderer,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
@@ -937,7 +936,7 @@ async def omni_init_app_state(
engine_client,
state.openai_serving_models,
args.response_role,
openai_serving_render=state.openai_serving_render,
online_renderer=state.online_renderer,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
@@ -964,7 +963,7 @@ async def omni_init_app_state(
OpenAIServingCompletion(
engine_client,
state.openai_serving_models,
openai_serving_render=state.openai_serving_render,
online_renderer=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,
@@ -1023,7 +1022,7 @@ async def omni_init_app_state(
)
state.serving_tokenization = ServingTokenization(
state.openai_serving_models,
state.openai_serving_render,
state.online_renderer,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
@@ -1055,7 +1054,7 @@ async def omni_init_app_state(
engine_client,
state.openai_serving_models,
args.response_role,
openai_serving_render=state.openai_serving_render,
online_renderer=state.online_renderer,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
@@ -1074,7 +1073,7 @@ async def omni_init_app_state(
ServingTokens(
engine_client,
state.openai_serving_models,
state.openai_serving_render,
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,