[CI] Update Dockerfile for vLLM installation and dependency management

- Added installation of vLLM from a precompiled wheel with a specific commit.
- Set LD_LIBRARY_PATH for CUDA compatibility with bitsandbytes.
- Upgraded flashinfer dependencies and ensured proper installation order for torch to avoid symbol issues.

docker/Dockerfile.ci

@@ -14,8 +14,48 @@ RUN apt-get update && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
+
+# Install vLLM (CUDA 13.0 build) from precompiled wheel at the selected commit.
+# Must use direct URL because the wheel has a PEP 440 local version identifier
+# (e.g. +gaeee7ef93.cu130) which pip/uv refuse to install from a PEP 503 package index.
+# The cu130 wheel index lives at /<commit>/cu130/vllm/ but the actual wheel files
+# are stored at the top level /<commit>/<wheel>.
+ENV VLLM_PRECOMPILED_WHEEL_COMMIT=ee0da84ab9e04ac7610e28580af62c365e898389
+# Ensure CUDA library path is in LD_LIBRARY_PATH so bitsandbytes' precompiled
+# C extension can find libnvJitLink.so.13 (CUDA 13.x JIT linker) at import time.
+# The base vLLM image has bitsandbytes pre-installed; without this env var,
+# worker subprocesses fail to load bitsandbytes' C extension, producing
+# OSError tracebacks that pollute CI logs.
+ENV LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib:${LD_LIBRARY_PATH}
+RUN VLLM_WHEEL_URL=$(python3 -c "import urllib.request,re; \
+    from urllib.parse import urljoin, quote; \
+    index_url='https://wheels.vllm.ai/${VLLM_PRECOMPILED_WHEEL_COMMIT}/cu130/vllm/'; \
+    html=urllib.request.urlopen(index_url).read().decode(); \
+    m=re.search(r'href=\"([^\"]*x86_64\.whl)\"',html); \
+    assert m, f'No x86_64 vLLM wheel found at {index_url}'; \
+    print(quote(urljoin(index_url,m.group(1)), safe=':/+%'))") && \
+    echo "Installing vLLM from: ${VLLM_WHEEL_URL}" && \
+    uv pip install --system --force-reinstall "${VLLM_WHEEL_URL}"
+
+
+
 RUN uv pip install --system ".[dev]"
 
+RUN uv pip install --system --upgrade \
+        "flashinfer-python==0.6.12" \
+        "flashinfer-cubin==0.6.12" \
+        "numpy==2.2.6"
+
+RUN uv pip install --system --upgrade \
+    "flashinfer-jit-cache==0.6.12" \
+    --index-url https://flashinfer.ai/whl/cu130
+
+# Force-reinstall torch AFTER flashinfer, because flashinfer --upgrade pulls in
+# a newer torch (2.12.x) whose libtorch_cuda.so lacks
+# at::cuda::getCurrentCUDABlasHandle, causing "undefined symbol" at import time.
+RUN uv pip install --system --force-reinstall \
+    "torch==2.11.0" "torchaudio==2.11.0" "torchvision==0.26.0" \
+    --torch-backend cu130
 
 RUN ln -sf /usr/bin/python3 /usr/bin/python