[Build] Automatically use the wheel of the base commit with Python-only build (#13178)

docs/source/getting_started/installation/gpu/cuda.inc.md

@@ -89,12 +89,22 @@ cd vllm
 VLLM_USE_PRECOMPILED=1 pip install --editable .
 ```
 
-This will download the [latest nightly wheel](https://wheels.vllm.ai/nightly/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl) and use the compiled libraries from there in the installation.
+This command will do the following:
+1. Look for the current branch in your vLLM clone.
+2. Identify the corresponding base commit in the main branch.
+3. Download the pre-built wheel of the base commit.
+4. Use its compiled libraries in the installation.
 
-The `VLLM_PRECOMPILED_WHEEL_LOCATION` environment variable can be used instead of `VLLM_USE_PRECOMPILED` to specify a custom path or URL to the wheel file. For example, to use the [0.6.1.post1 PyPi wheel](https://pypi.org/project/vllm/#files):
+:::{note}
+1. If you change C++ or kernel code, you cannot use Python-only build; otherwise you will see an import error about library not found or undefined symbol.
+2. If you rebase your dev branch, it is recommended to uninstall vllm and re-run the above command to make sure your libraries are up to date.
+:::
+
+In case you see an error about wheel not found when running the above command, it might be because the commit you based on in the main branch was just merged and the wheel is being built. In this case, you can wait for around an hour to try again, or manually assign the previous commit in the installation using the `VLLM_PRECOMPILED_WHEEL_LOCATION` environment variable.
 
 ```console
-export VLLM_PRECOMPILED_WHEEL_LOCATION=https://files.pythonhosted.org/packages/4a/4c/ee65ba33467a4c0de350ce29fbae39b9d0e7fcd887cc756fa993654d1228/vllm-0.6.3.post1-cp38-abi3-manylinux1_x86_64.whl
+export VLLM_COMMIT=72d9c316d3f6ede485146fe5aabd4e61dbc59069 # use full commit hash from the main branch
+export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
 pip install --editable .
 ```
 

setup.py

@@ -268,15 +268,34 @@ class cmake_build_ext(build_ext):
 
 class repackage_wheel(build_ext):
     """Extracts libraries and other files from an existing wheel."""
-    default_wheel = "https://wheels.vllm.ai/nightly/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl"
 
-    def run(self) -> None:
-        wheel_location = os.getenv("VLLM_PRECOMPILED_WHEEL_LOCATION",
-                                   self.default_wheel)
+    def get_base_commit_in_main_branch(self) -> str:
+        import subprocess
+
+        try:
+            current_branch = subprocess.check_output(
+                ["git", "branch", "--show-current"]).decode("utf-8").strip()
+
+            base_commit = subprocess.check_output(
+                ["git", "merge-base", "main",
+                 current_branch]).decode("utf-8").strip()
+            return base_commit
+        except Exception as err:
+            logger.warning(
+                "Failed to get the base commit in the main branch. "
+                "Using the nightly wheel. The libraries in this "
+                "wheel may not be compatible with your dev branch: %s", err)
+            return "nightly"
 
+    def run(self) -> None:
         assert _is_cuda(
         ), "VLLM_USE_PRECOMPILED is only supported for CUDA builds"
 
+        wheel_location = os.getenv("VLLM_PRECOMPILED_WHEEL_LOCATION", None)
+        if wheel_location is None:
+            base_commit = self.get_base_commit_in_main_branch()
+            wheel_location = f"https://wheels.vllm.ai/{base_commit}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl"
+
         import zipfile
 
         if os.path.isfile(wheel_location):