[Rebase] Rebase to vllm 0.27.0 (#5976)

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 2026-08-11 15:23:46 +00:00
1 parent 584d78c673
commit 2ce15ab7a0
55 files changed
+1335 -93

No files matched your search

+14 -2
View File
@@ -152,6 +152,7 @@ from vllm_omni.entrypoints.openai.video_api_utils import (
decode_input_reference,
)
from vllm_omni.entrypoints.openpi.serving import ServingRealtimeRobotOpenPI
from vllm_omni.entrypoints.utils import PureDiffusionLauncherAdapter
from vllm_omni.errors import OmniClientError
from vllm_omni.inputs.data import OmniDiffusionSamplingParams, OmniTextPrompt
from vllm_omni.utils.forced_aligner import build_forced_aligner_config
@@ -549,6 +550,16 @@ async def omni_run_server_worker(listen_address, sock, args, client_config=None,
"Starting vLLM API server (pure diffusion mode) on %s",
listen_address,
)
# The vLLM 0.27 launcher's shutdown path reads
# engine_client.vllm_config.shutdown_timeout; AsyncOmni.vllm_config
# is None for pure diffusion (no comprehension stage), which would
# crash handle_shutdown and hang teardown. Wrap app.state.engine_client
# with a shim that only overrides vllm_config and forwards everything
# else (get_vllm_config still returns None for pure-diffusion detection).
app.state.engine_client = PureDiffusionLauncherAdapter(
engine_client,
shutdown_timeout=getattr(args, "shutdown_timeout", 0),
)
else:
logger.info(
"Starting vLLM API server %d on %s",
@@ -985,8 +996,9 @@ async def omni_init_app_state(
)
# Warm up chat template processing to avoid first-request latency
if state.openai_serving_chat is not None:
state.openai_serving_chat.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(