[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>
This commit is contained in:
Chenxi Qian
2025-11-28 18:06:39 +08:00
committed by GitHub
parent 3199fe8350
commit 554f16ae1f
50 changed files with 6934 additions and 7 deletions

View File

@@ -12,7 +12,7 @@ repos:
- id: codespell
args: [
--toml, pyproject.toml,
'--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/mla_preprocess/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
'--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND'
]
additional_dependencies:
@@ -37,7 +37,7 @@ repos:
- id: typos
args: [
"--force-exclude",
"--exclude", "csrc/mla_preprocess/**"
"--exclude", "csrc/**"
]
- repo: https://github.com/PyCQA/isort
rev: 6.0.1