Files
xc-llm-ascend/pyproject.toml
Chenxi Qian 554f16ae1f [Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)
### What this PR does / why we need it?

This PR introduces support for adding custom CANN `aclnn` ops to
`vllm-ascend`, allowing users to define and use their own custom
operators.

Key changes include:
- Building and installing custom ops into the `vllm-ascend`-specified
directory
- Binding the `aclnn` op interface to the `torch.ops._C_ascend` module
- Enabling invocation of these ops within `vllm-ascend`

This PR includes a sample custom op:
`aclnnGroupedMatmulSwigluQuantWeightNzTensorList`, which is adapted from
the CANN operator
[`aclnnGroupedMatmulSwigluQuantWeightNZ`](https://www.hiascend.com/document/detail/zh/canncommercial/83RC1/API/aolapi/context/aclnnGroupedMatmulSwigluQuantWeightNZ.md).
Its input parameters `weight` and `weight_scale` now accept
`list[torch.Tensor]` (i.e., `at::TensorList`).

### Does this PR introduce _any_ user-facing change?

No.


- vLLM version: v0.11.2

---------

Signed-off-by: QianChenxi <chenxi.qian.cq@outlook.com>
2025-11-28 18:06:39 +08:00

43 lines
1.1 KiB
TOML

[build-system]
# Should be mirrored in requirements.txt
requires = [
"attrs",
"cmake>=3.26",
"decorator",
"einops",
"googleapis-common-protos",
"numpy<2.0.0",
"packaging",
"pip",
"pybind11",
"pyyaml",
"scipy",
"pandas",
"pandas-stubs",
"psutil",
"setuptools>=64",
"setuptools-scm>=8",
"transformers<=4.57.1",
"torch-npu==2.7.1",
"torch==2.7.1",
"torchvision",
"wheel",
"msgpack",
"quart",
"numba",
"opencv-python-headless<=4.11.0.86", # Required to avoid numpy version conflict with vllm
"compressed_tensors>=0.11.0"
]
build-backend = "setuptools.build_meta"
[tool.pymarkdown]
plugins.md004.style = "sublist" # ul-style
plugins.md007.indent = 4 # ul-indent
plugins.md007.start_indented = true # ul-indent
plugins.md013.enabled = false # line-length
plugins.md041.enabled = false # first-line-h1
plugins.md033.enabled = false # inline-html
plugins.md046.enabled = false # code-block-style
plugins.md024.allow_different_nesting = true # no-duplicate-headers
plugins.md029.enabled = false # ol-prefix