Bump torch version to 2.7.1 (#1562)

### What this PR does / why we need it?
Bump torch version to 2.7.1, and cleanup infer schema patch
https://github.com/vllm-project/vllm-ascend/commit/857f489
(https://github.com/vllm-project/vllm-ascend/pull/837), this patch
depends on also: https://github.com/vllm-project/vllm-ascend/pull/1974

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

#### How was this patch tested?
CI passed

torch-npu 2.7.1rc1 install guide:
https://gitee.com/ascend/pytorch/tree/v2.7.1/
install depending:
```
pip3 install pyyaml
pip3 install setuptools
```
install torch-npu:

Closes: https://github.com/vllm-project/vllm-ascend/issues/1866
Closes: https://github.com/vllm-project/vllm-ascend/issues/1390


- vLLM version: v0.10.0
- vLLM main:
9af654cc38

---------

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>

vllm_ascend/patch/__init__.py

@@ -75,20 +75,6 @@
 #    Future Plan:
 #       Remove this patch when vllm merged them.
 #
-# ** File: worker/patch_common/patch_utils.py **
-# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-#   1. `vllm.utils.direct_register_custom_op`
-#    Why:
-#       pytorch 2.7.o is not compatible with pytorch 2.5.1. While vllm is based on pytorch 2.7.0, but vllm ascend
-#       is based on pytorch 2.5.1, so we need to use this patch to make vllm compatible with pytorch 2.5.1.
-#    How：
-#       patch __annotations__ check to make it compatible with pytorch 2.5.1.
-#    Related PR (if no, explain why):
-#       This is the problem in vllm-ascend
-#    Future Plan:
-#       Remove this patch once pytorch 2.7.0 is supported for vllm ascend.
-#
-# ** File: worker/patch_0_10_0/patch_sampler_gather_logprobs.py **
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #   1. `vllm.v1.sample.sampler.Sampler.gather_logprobs`
 #    Why:

vllm_ascend/patch/worker/patch_common/__init__.py

@@ -15,9 +15,6 @@
 # limitations under the License.
 #
 
-# patch_utils should be the first import, because it will be used by other
-# patch files.
-import vllm_ascend.patch.worker.patch_common.patch_utils  # noqa isort:skip
 import vllm_ascend.patch.worker.patch_common.patch_distributed  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_linear  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_minicpm  # noqa

vllm_ascend/patch/worker/patch_common/patch_utils.py

@@ -1,38 +0,0 @@
-from typing import Callable, List, Optional, Tuple
-
-import torch
-from torch.library import Library
-from vllm import utils
-from vllm.utils import vllm_lib
-
-
-def ascend_direct_register_custom_op(
-        op_name: str,
-        op_func: Callable,
-        mutates_args: list[str],
-        fake_impl: Optional[Callable] = None,
-        target_lib: Optional[Library] = None,
-        dispatch_key: str = "CUDA",
-        tags: Tuple[torch.Tag, ...] = (),
-):
-    # In pytorch 2.5.1, torch.library.infer_schema require the input function to
-    # have annotations supported by typing library. But in pytorch 2.7.0 which
-    # vllm using, torch.library.infer_schema require the python builtin type. In
-    # this case, we should revert built type to typing type for 2.5.1 backward
-    # compatibility.
-    for k, v in op_func.__annotations__.items():
-        if v == list[int]:
-            op_func.__annotations__[k] = List[int]
-        if v == Optional[list[int]]:
-            op_func.__annotations__[k] = Optional[List[int]]
-        # TODO: add more type convert here if needed.
-    import torch.library
-    schema_str = torch.library.infer_schema(op_func, mutates_args=mutates_args)
-    my_lib = target_lib or vllm_lib
-    my_lib.define(op_name + schema_str, tags=tags)
-    my_lib.impl(op_name, op_func, dispatch_key=dispatch_key)
-    if fake_impl is not None:
-        my_lib._register_fake(op_name, fake_impl)
-
-
-utils.direct_register_custom_op = ascend_direct_register_custom_op