Re-patch TritonPlaceholder on main to make CI happy (#753)

### What this PR does / why we need it?
Re-patch TritonPlaceholder on main to make CI happy
- Add triton patch back until
https://github.com/vllm-project/vllm/pull/17446 resolved
- Move patch_main before patch_common to resolve minicpm triton import
issue
- Add `0.8.5` and `0.8.5.post1` to make patch work on 0.8.5 all versions

Related:
- https://github.com/vllm-project/vllm-ascend/pull/704
- https://github.com/vllm-project/vllm-ascend/pull/690

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
All CI passed include main

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>

vllm_ascend/__init__.py

@@ -23,5 +23,9 @@ def register():
 
 
 def register_model():
+    # TODO: fixme when TritonPlaceholder fixed
+    from vllm_ascend.utils import vllm_version_is
+    if not (vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1")):
+        import vllm_ascend.patch.worker.patch_main.patch_tritonplaceholder  # noqa
     from .models import register_model
     register_model()

vllm_ascend/patch/__init__.py

@@ -158,4 +158,15 @@
 #       - https://github.com/vllm-project/vllm-ascend/pull/395
 #    Future Plan:
 #       Revert it when the related pr is merged in vllm and vllm-ascend.
-#
+#
+# ** File: worker/patch_main/patch_tritonplaceholder.py **
+# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#   1. `triton` Module
+#    Why:
+#       Triton is not supported on npu currently, importing triton will break vllm-ascend
+#    How：
+#       ditto
+#    Related PR (if no, explain why): vllm haven't support yet
+#       TritonPlaceholder is only available in vllm>0.8.5.post1
+#    Future Plan:
+#       https://github.com/vllm-project/vllm/pull/17446

vllm_ascend/patch/platform/__init__.py

@@ -17,7 +17,7 @@
 from vllm_ascend.utils import vllm_version_is
 
 # Import specific patches for different versions
-if vllm_version_is("0.8.5"):
+if vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1"):
     from vllm_ascend.patch.platform import patch_0_8_5  # noqa: F401
     from vllm_ascend.patch.platform import patch_common  # noqa: F401
 else:

vllm_ascend/patch/worker/__init__.py

@@ -18,9 +18,9 @@
 from vllm_ascend.utils import vllm_version_is
 
 # Import specific patches for different versions
-if vllm_version_is("0.8.5"):
+if vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1"):
     from vllm_ascend.patch.worker import patch_0_8_5  # noqa: F401
     from vllm_ascend.patch.worker import patch_common  # noqa: F401
 else:
+    from vllm_ascend.patch.worker import patch_main  # noqa: F401 # isort:skip
     from vllm_ascend.patch.worker import patch_common  # noqa: F401
-    from vllm_ascend.patch.worker import patch_main  # noqa: F401

vllm_ascend/patch/worker/patch_main/__init__.py

@@ -13,4 +13,5 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
+#
+import vllm_ascend.patch.worker.patch_main.patch_tritonplaceholder  # noqa

vllm_ascend/patch/worker/patch_main/patch_tritonplaceholder.py

@@ -0,0 +1,71 @@
+#
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
+# Copyright 2023 The vLLM team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# This file is a part of the vllm-ascend project.
+# Adapted from vllm/triton_utils/importing.py
+#
+
+import importlib
+import sys
+import types
+from importlib.util import find_spec
+
+from vllm.logger import logger
+
+HAS_TRITON = (
+    find_spec("triton") is not None
+    or find_spec("pytorch-triton-xpu") is not None  # Not compatible
+)
+
+if not HAS_TRITON:
+    logger.info("Triton not installed or not compatible; certain GPU-related"
+                " functions will not be available.")
+
+    class TritonPlaceholder(types.ModuleType):
+
+        def __init__(self):
+            super().__init__("triton")
+            self.jit = self._dummy_decorator("jit")
+            self.autotune = self._dummy_decorator("autotune")
+            self.heuristics = self._dummy_decorator("heuristics")
+            self.language = TritonLanguagePlaceholder()
+            self.__spec__ = importlib.machinery.ModuleSpec(
+                name="triton", loader=None, origin="placeholder")
+            logger.warning_once(
+                "Triton is not installed. Using dummy decorators. "
+                "Install it via `pip install triton` to enable kernel"
+                " compilation.")
+
+        def _dummy_decorator(self, name):
+
+            def decorator(func=None, **kwargs):
+                if func is None:
+                    return lambda f: f
+                return func
+
+            return decorator
+
+    class TritonLanguagePlaceholder(types.ModuleType):
+
+        def __init__(self):
+            super().__init__("triton.language")
+            self.constexpr = None
+            self.dtype = None
+
+    sys.modules['triton'] = TritonPlaceholder()
+    sys.modules['triton.language'] = TritonLanguagePlaceholder()
+
+if 'triton' in sys.modules:
+    logger.info("Triton module has been replaced with a placeholder.")