EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Bump torch version to 2.7.1 (#1562)

Browse Source 
### 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>
This commit is contained in:
leo-pony
2025-08-05 08:43:24 +08:00
committed by GitHub
parent 36e450eb0f
commit 807f0895b2
15 changed files with 14 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
tests/ut/patch/worker/patch_common/test_patch_utils.py
View File

@@ -1,104 +0,0 @@
#
# 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.
#
from typing import List, Optional
from unittest.mock import MagicMock, patch
import torch
from torch.library import Library
from tests.ut.base import TestBase
from vllm_ascend.patch.worker.patch_common.patch_utils import \
ascend_direct_register_custom_op
class TestPatchUtils(TestBase):
def setUp(self):
super().setUp()
self.mock_op_func = MagicMock()
self.mock_op_func.__annotations__ = {
'param1': list[int],
'param2': Optional[list[int]],
'param3': str
}
self.mock_fake_impl = MagicMock()
self.mock_lib = MagicMock(spec=Library)
self.op_name = "test_op"
self.mutates_args = ["arg1"]
self.dispatch_key = "NPU"
self.tags = (torch.Tag.pt2_compliant_tag, )
self.patch_infer_schema = patch(
'vllm_ascend.patch.worker.patch_common.patch_utils.torch.library.infer_schema'
)
self.patch_vllm_lib = patch(
'vllm_ascend.patch.worker.patch_common.patch_utils.vllm_lib')
self.mock_infer_schema = self.patch_infer_schema.start()
self.mock_vllm_lib = self.patch_vllm_lib.start()
self.addCleanup(self.patch_infer_schema.stop)
self.addCleanup(self.patch_vllm_lib.stop)
def test_utils_patched(self):
from vllm import utils
self.assertIs(utils.direct_register_custom_op,
ascend_direct_register_custom_op)
def test_register_with_default_lib(self):
self.mock_infer_schema.return_value = "(Tensor self) -> Tensor"
ascend_direct_register_custom_op(op_name=self.op_name,
op_func=self.mock_op_func,
mutates_args=self.mutates_args,
fake_impl=self.mock_fake_impl,
dispatch_key=self.dispatch_key,
tags=self.tags)
self.assertEqual(self.mock_op_func.__annotations__['param1'],
List[int])
self.assertEqual(self.mock_op_func.__annotations__['param2'],
Optional[List[int]])
self.assertEqual(self.mock_op_func.__annotations__['param3'], str)
self.mock_infer_schema.assert_called_once_with(
self.mock_op_func, mutates_args=self.mutates_args)
self.mock_vllm_lib.define.assert_called_once_with(
f"{self.op_name}(Tensor self) -> Tensor", tags=self.tags)
self.mock_vllm_lib.impl.assert_called_once_with(
self.op_name, self.mock_op_func, dispatch_key=self.dispatch_key)
self.mock_vllm_lib._register_fake.assert_called_once_with(
self.op_name, self.mock_fake_impl)
def test_register_with_custom_lib(self):
self.mock_infer_schema.return_value = "(Tensor a, Tensor b) -> Tensor"
ascend_direct_register_custom_op(op_name=self.op_name,
op_func=self.mock_op_func,
mutates_args=self.mutates_args,
target_lib=self.mock_lib)
self.mock_lib.define.assert_called_once_with(
f"{self.op_name}(Tensor a, Tensor b) -> Tensor", tags=())
self.mock_lib.impl.assert_called_once_with(self.op_name,
self.mock_op_func,
dispatch_key="CUDA")
self.mock_lib._register_fake.assert_not_called()