vllm_cmakelists.patch

# ============================================================================
# vLLM CMakeLists.txt Patch for DGX Spark (GB10)
# ============================================================================
# This patch removes SM12.0/12.1 architectures from certain CUDA kernel
# compilations that have issues on DGX Spark's GB10 GPU.
#
# The GB10 GPU has compute capability 12.1, but certain FP4 and scaled_mm
# kernels compiled for SM12.x cause runtime errors. This patch restricts
# those kernels to SM10.0 (Hopper) architecture only, while still allowing
# the main model to run on SM12.x.
# ============================================================================

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 7cb94f919..f860e533e 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -594,9 +594,9 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")

   # FP4 Archs and flags
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
-    cuda_archs_loose_intersection(FP4_ARCHS "10.0f;11.0f;12.0f" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(FP4_ARCHS "10.0f" "${CUDA_ARCHS}")
   else()
-    cuda_archs_loose_intersection(FP4_ARCHS "10.0a;10.1a;12.0a;12.1a" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(FP4_ARCHS "10.0a;10.1a" "${CUDA_ARCHS}")
   endif()
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
     set(SRCS
@@ -668,7 +668,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   endif()

   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
-    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f;11.0f" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f" "${CUDA_ARCHS}")
   else()
     cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a" "${CUDA_ARCHS}")
   endif()
@@ -716,9 +716,9 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   endif()

   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
-    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f;11.0f;12.0f" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f" "${CUDA_ARCHS}")
   else()
-    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a;10.1a;10.3a;12.0a;12.1a" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a;10.1a;10.3a" "${CUDA_ARCHS}")
   endif()
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND SCALED_MM_ARCHS)
     set(SRCS "csrc/quantization/w8a8/cutlass/moe/blockwise_scaled_group_mm_sm100.cu")