Refactor Dockerfile.ci to install vLLM from source using precompiled artifacts at a specified commit. This change replaces the previous wheel installation method and ensures the correct versioning of dependencies. Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

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

docker/Dockerfile.ci

@@ -11,20 +11,20 @@ RUN apt-get update && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Install vLLM wheel for the specific commit
-# URL format: https://wheels.vllm.ai/<commit_hash>/
-# Current vLLM wheel commit: 097eb544e9a22810c9b7a59e586b61627b308362
-# 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/2754231ba3a72f41e62922d1552c33e8f3f6a9d1
+# Install vLLM from source at the selected commit using precompiled artifacts
+ARG VLLM_COMMIT=2754231ba3a72f41e62922d1552c33e8f3f6a9d1
+RUN git clone https://github.com/vllm-project/vllm.git /workspace/vllm && \
+    cd /workspace/vllm && \
+    git checkout ${VLLM_COMMIT} && \
+    (uv pip uninstall --system -y vllm || true) && \
+    VLLM_USE_PRECOMPILED=1 uv pip install --system -e . && \
+    cd ${APP_DIR} && \
+    uv pip install --system ".[dev]" && \
+    uv pip install --system --upgrade \
+        "flashinfer-cubin==0.6.4" \
+        "nvidia-cublas-cu12==12.9.1.4" \
+        "numpy==2.2.6"
 
-RUN uv pip install --system --no-cache-dir ".[dev]"
-
-RUN uv pip install --system --upgrade \
-    "flashinfer-cubin==0.6.4" \
-    "nvidia-cublas-cu12==12.9.1.4" \
-    "numpy==2.2.6"
 RUN uv pip install --system --upgrade \
     "flashinfer-jit-cache==0.6.4" \
     --index-url https://flashinfer.ai/whl/cu129