52086394ae
### What this PR does / why we need it?
Convert `vllm-ascend/compilation` to ruff format.
### Does this PR introduce _any_ user-facing change?
During this migration, we encountered some **errors** in our CI and
testing environments, such as:
```
vllm_ascend/utils.py:653: in <module>
def register_ascend_customop(vllm_config: VllmConfig | None = None):
^^^^^^^^^^^^^^^^^
E TypeError: unsupported operand type(s) for |: 'NoneType' and 'NoneType'
```
**1. Root Cause Analysis:**
The project uses a common pattern to break circular dependencies:
```python
if TYPE_CHECKING:
from vllm.config import VllmConfig
else:
VllmConfig = None # Placeholder assigned at runtime
```
When Python parses the function definition `def
register_ascend_customop(vllm_config: VllmConfig | None)`, it attempts
to evaluate the expression `VllmConfig | None`.
Since `VllmConfig` is assigned `None` at runtime, the expression
effectively becomes `None | None`. In Python, `None` is an instance of
`NoneType`. While the `|` operator is implemented for Type objects
(classes), it is not supported for `NoneType` instances, leading to the
`TypeError` shown above.
**2. Solution:**
To maintain the modern `|` syntax required by our new linting standards
while preserving our dependency management strategy, I have introduced:
```python
from __future__ import annotations
```
at the top of the affected files. This enables **Postponed Evaluation of
Annotations (PEP 563)**.
**3. Impact and Benefits:**
- By enabling `annotations`, Python no longer executes the `VllmConfig |
None` operation during module load. Instead, it stores the annotation as
a string literal, completely avoiding the `None | None` calculation.
- We can keep the `VllmConfig = None` placeholders. This ensures that
other modules can still import these symbols without triggering an
`ImportError`, maintaining a stable dependency graph.
- IDEs and static type checkers (MyPy/Pyright) continue to resolve the
types correctly. This allows us to use modern syntax without sacrificing
type safety or runtime stability.
- The only side effect is that `__annotations__` will now return strings
instead of type objects. Since this module does not use runtime type
enforcement or reflection, this change has zero negative impact on
existing functionality.
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
11b6af5280
---------
Signed-off-by: MrZ20 <2609716663@qq.com>
61 lines
2.2 KiB
Python
61 lines
2.2 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
#
|
|
# 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.
|
|
#
|
|
|
|
from torch import fx as fx
|
|
from vllm.compilation.inductor_pass import get_pass_context
|
|
from vllm.compilation.vllm_inductor_pass import VllmInductorPass
|
|
from vllm.config import VllmConfig
|
|
|
|
|
|
class GraphFusionPassManager:
|
|
"""
|
|
A pass manager for graph fusion passes.
|
|
It handles the configuration and execution of passes.
|
|
The counterpart in vllm is PostGradPassManager. Since torch_npu
|
|
does not support triton for now, we define our own pass manager.
|
|
"""
|
|
|
|
def __init__(self):
|
|
self.passes: list[VllmInductorPass] = []
|
|
|
|
def __call__(self, graph: fx.Graph) -> fx.Graph:
|
|
compile_range = get_pass_context().compile_range
|
|
|
|
for pass_ in self.passes:
|
|
if pass_.is_applicable_for_range(compile_range):
|
|
pass_(graph)
|
|
graph.recompile()
|
|
return graph
|
|
|
|
def add(self, pass_: VllmInductorPass):
|
|
assert isinstance(pass_, VllmInductorPass)
|
|
self.passes.append(pass_)
|
|
|
|
def configure(self, config: VllmConfig):
|
|
# By default, we enable the graph fusion and quantization fusion pass.
|
|
self.ascend_compilation_config: dict = config.additional_config.get("ascend_compilation_config", {})
|
|
if self.ascend_compilation_config.get("fuse_norm_quant", True):
|
|
from .passes.norm_quant_fusion_pass import AddRMSNormQuantFusionPass
|
|
|
|
self.passes.append(AddRMSNormQuantFusionPass(config))
|
|
|
|
if self.ascend_compilation_config.get("fuse_qknorm_rope", True):
|
|
from .passes.qknorm_rope_fusion_pass import QKNormRopeFusionPass
|
|
|
|
self.passes.append(QKNormRopeFusionPass(config))
|