Merge branch 'upstream' into improve-types

.buildkite/check-wheel-size.py

@@ -1,7 +1,7 @@
 import os
 import zipfile
 
-MAX_SIZE_MB = 150
+MAX_SIZE_MB = 200
 
 
 def print_top_10_largest_files(zip_file):

.buildkite/run-amd-test.sh

@@ -5,6 +5,34 @@ set -ex
 echo "--- ROCm info"
 rocminfo
 
+# cleanup older docker images
+cleanup_docker() {
+  # Get Docker's root directory
+  docker_root=$(docker info -f '{{.DockerRootDir}}')
+  if [ -z "$docker_root" ]; then
+    echo "Failed to determine Docker root directory."
+    exit 1
+  fi
+  echo "Docker root directory: $docker_root"
+  # Check disk usage of the filesystem where Docker's root directory is located
+  disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//')
+  # Define the threshold
+  threshold=70
+  if [ "$disk_usage" -gt "$threshold" ]; then
+    echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..."
+    # Remove dangling images (those that are not tagged and not used by any container)
+    docker image prune -f
+    # Remove unused volumes
+    docker volume prune -f
+    echo "Docker images and volumes cleanup completed."
+  else
+    echo "Disk usage is below $threshold%. No cleanup needed."
+  fi
+}
+
+# Call the cleanup docker function
+cleanup_docker
+
 echo "--- Resetting GPUs"
 
 echo "reset" > /opt/amdgpu/etc/gpu_state

CMakeLists.txt

@@ -177,7 +177,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   include(FetchContent)
   SET(CUTLASS_ENABLE_HEADERS_ONLY=ON)
   FetchContent_Declare(
-        cutlass 
+        cutlass
         GIT_REPOSITORY https://github.com/nvidia/cutlass.git
         # CUTLASS 3.5.0
         GIT_TAG 7d49e6c7e2f8896c47f586706e67e1fb215529dc
@@ -200,11 +200,13 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   # The CUTLASS kernels for Hopper require sm90a to be enabled.
   # This is done via the below gencode option, BUT that creates kernels for both sm90 and sm90a.
   # That adds an extra 17MB to compiled binary, so instead we selectively enable it.
-  set_source_files_properties(
-      "csrc/quantization/cutlass_w8a8/scaled_mm_dq_c3x.cu"
-      PROPERTIES
-      COMPILE_FLAGS
-      "-gencode arch=compute_90a,code=sm_90a")
+  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 12.0)
+    set_source_files_properties(
+          "csrc/quantization/cutlass_w8a8/scaled_mm_dq_c3x.cu"
+          PROPERTIES
+          COMPILE_FLAGS
+          "-gencode arch=compute_90a,code=sm_90a")
+  endif()
 
 endif()