Update Dockerfile.ci to install a new version of vllm from a different extra index URL. Refactor import statement in serving_chat.py to use the correct BaseRenderer module path.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

docker/Dockerfile.ci

@@ -18,7 +18,7 @@ RUN apt-get update && \
 # Note: --prerelease=allow is required because nightly/commit wheels use
 # pre-release version numbers (e.g. 2.10.0.dev...) which uv ignores by default,
 # causing it to fall back to the older stable release from PyPI.
-RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/4a1550d22d7058e129d0e1257e726b3bf4a77025
+RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/ec12d39d44739bee408ec1473acc09e75daf1a5d
 
 # # Keep flashinfer runtime packages in version sync.
 # # We derive the version from installed flashinfer (pulled by vllm)

vllm_omni/entrypoints/openai/serving_chat.py

@@ -13,7 +13,7 @@ import torch
 from fastapi import Request
 from PIL import Image
 from pydantic import TypeAdapter
-from vllm.renderers.protocol import BaseRenderer
+from vllm.renderers.base import BaseRenderer
 
 from vllm_omni.entrypoints.async_omni import AsyncOmni
 from vllm_omni.entrypoints.openai.protocol.chat_completion import OmniChatCompletionResponse