[CI][CPU] Improve dummy Triton interfaces and fix the CPU CI (#19838)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

requirements/cpu.txt

@@ -21,9 +21,6 @@ torchvision; platform_machine != "ppc64le" and platform_machine != "s390x"
 torchvision==0.22.0; platform_machine == "ppc64le"
 datasets # for benchmark scripts
 
-# cpu cannot use triton 3.3.0
-triton==3.2.0; platform_machine == "x86_64"
-
 # Intel Extension for PyTorch, only for x86_64 CPUs
 intel-openmp==2024.2.1; platform_machine == "x86_64"
 intel_extension_for_pytorch==2.7.0; platform_machine == "x86_64"

vllm/triton_utils/importing.py

@@ -68,9 +68,11 @@ class TritonPlaceholder(types.ModuleType):
 
     def __init__(self):
         super().__init__("triton")
+        self.__version__ = "3.3.0"
         self.jit = self._dummy_decorator("jit")
         self.autotune = self._dummy_decorator("autotune")
         self.heuristics = self._dummy_decorator("heuristics")
+        self.Config = self._dummy_decorator("Config")
         self.language = TritonLanguagePlaceholder()
         logger.warning_once(
             "Triton is not installed. Using dummy decorators. "