[Rebase] Rebase to vllm 0.28.0 (#6606)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Zhou TaichangandClaude Opus 5 authored and GitHub committed 2026-08-27 06:12:55 +00:00
1 parent da4a08b65b
commit 651b03225b
42 files changed
+931 -121

No files matched your search

+5 -7
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
import asyncio
import base64
import dataclasses
@@ -64,6 +64,7 @@ from vllm.entrypoints.pooling.embed.serving import ServingEmbedding as OpenAISer
from vllm.entrypoints.pooling.pooling.serving import ServingPooling
from vllm.entrypoints.pooling.scoring.serving import ServingScores
from vllm.entrypoints.scale_out.token_in_token_out.serving import ServingTokens
from vllm.entrypoints.serve import create_error_response
# vLLM moved `base` from openai.basic.api_router to serve.instrumentator.basic.
# Keep a fallback for older/newer upstream layouts during rebase windows.
@@ -75,7 +76,6 @@ from vllm.entrypoints.serve.utils.api_utils import (
validate_json_request,
with_cancellation,
)
from vllm.entrypoints.serve.utils.error_response import create_error_response
from vllm.entrypoints.serve.utils.orca_metrics import metrics_header
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.entrypoints.serve.utils.server_utils import get_uvicorn_log_config
@@ -997,11 +997,9 @@ async def omni_init_app_state(
)
# Warm up chat template processing to avoid first-request latency
# Upstream f5ffc59b6a moved warmup onto OnlineRenderer. Accelerator
# images can temporarily lag that renderer API, where warmup is optional.
renderer_warmup = getattr(state.online_renderer, "warmup", None)
if renderer_warmup is not None:
renderer_warmup()
# Upstream f5ffc59b6a removed OpenAIServingChat.warmup() and moved the
# warmup onto the renderer (OnlineRenderer.warmup()); mirror upstream.
state.online_renderer.warmup()
state.openai_serving_completion = (
OpenAIServingCompletion(