[CI/Build] Support compilation with local cutlass path (#10423) (#10424)

CMakeLists.txt

@@ -206,6 +206,18 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   # Set CUTLASS_REVISION manually -- its revision detection doesn't work in this case.
   set(CUTLASS_REVISION "v3.5.1" CACHE STRING "CUTLASS revision to use")
 
+  # Use the specified CUTLASS source directory for compilation if VLLM_CUTLASS_SRC_DIR is provided
+  if (DEFINED ENV{VLLM_CUTLASS_SRC_DIR})
+    set(VLLM_CUTLASS_SRC_DIR $ENV{VLLM_CUTLASS_SRC_DIR})
+  endif()
+
+  if(VLLM_CUTLASS_SRC_DIR)
+    if(NOT IS_ABSOLUTE VLLM_CUTLASS_SRC_DIR)
+      get_filename_component(VLLM_CUTLASS_SRC_DIR "${VLLM_CUTLASS_SRC_DIR}" ABSOLUTE)
+    endif()
+    message(STATUS "The VLLM_CUTLASS_SRC_DIR is set, using ${VLLM_CUTLASS_SRC_DIR} for compilation")
+    FetchContent_Declare(cutlass SOURCE_DIR ${VLLM_CUTLASS_SRC_DIR})
+  else()
     FetchContent_Declare(
         cutlass
         GIT_REPOSITORY https://github.com/nvidia/cutlass.git
@@ -217,6 +229,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
         # So if the GIT_TAG above is updated to a commit hash, GIT_SHALLOW must be set to FALSE
         GIT_SHALLOW TRUE
     )
+  endif()
   FetchContent_MakeAvailable(cutlass)
 
   list(APPEND VLLM_EXT_SRC

docs/source/getting_started/installation.rst

@@ -170,6 +170,18 @@ To build vLLM using an existing PyTorch installation:
     $ pip install -e . --no-build-isolation
 
 
+Use the local cutlass for compilation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Currently, before starting the build process, vLLM fetches cutlass code from GitHub. However, there may be scenarios where you want to use a local version of cutlass instead.
+To achieve this, you can set the environment variable VLLM_CUTLASS_SRC_DIR to point to your local cutlass directory.
+
+.. code-block:: console
+
+    $ git clone https://github.com/vllm-project/vllm.git
+    $ cd vllm
+    $ VLLM_CUTLASS_SRC_DIR=/path/to/cutlass pip install -e .
+
+
 Troubleshooting
 ~~~~~~~~~~~~~~~