99aedaff63
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
|` vllm_ascend/quantization/compressed_tensors/compressed_tensors.py`|
|` vllm_ascend/quantization/quant_config.py`|
|` vllm_ascend/quantization/utils.py`|
|` vllm_ascend/quantization/w4a16.py`|
|` vllm_ascend/quantization/w4a4_flatquant_dynamic.py`|
|` vllm_ascend/quantization/w4a8_dynamic.py`|
|` vllm_ascend/quantization/w8a16.py`|
|` vllm_ascend/quantization/w8a8.py`|
|` vllm_ascend/quantization/w8a8_dynamic.py`|
|` vllm_ascend/quantization/w8a8_pdmix.py`|
|` vllm_ascend/quantization/w8a8mxfp8.py`|
|` vllm_ascend/sample/rejection_sampler.py`|
|` vllm_ascend/sample/sampler.py`|
|` vllm_ascend/worker/block_table.py`|
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2c24bc6996
Signed-off-by: MrZ20 <2609716663@qq.com>
119 lines
2.7 KiB
TOML
119 lines
2.7 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>=4.57.4",
|
|
"torch-npu==2.9.0",
|
|
"torch==2.9.0",
|
|
"torchvision",
|
|
"wheel",
|
|
"msgpack",
|
|
"quart",
|
|
"numba",
|
|
"xgrammar>=0.1.30",
|
|
"fastapi<0.124.0",
|
|
"opencv-python-headless<=4.11.0.86", # Required to avoid numpy version conflict with vllm
|
|
"compressed_tensors>=0.11.0",
|
|
"arctic-inference==0.1.1",
|
|
"triton-ascend==3.2.0"
|
|
]
|
|
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
|
|
|
|
[tool.ruff]
|
|
# TODO: according to PEP8, there should be 80 characters per line
|
|
line-length = 120
|
|
# Folder to be modified
|
|
exclude = [
|
|
"tests/**",
|
|
|
|
# (8)
|
|
"vllm_ascend/ops/__init__.py",
|
|
"vllm_ascend/ops/activation.py",
|
|
"vllm_ascend/ops/flashcomm2_oshard_manager.py",
|
|
"vllm_ascend/ops/layernorm.py",
|
|
"vllm_ascend/ops/mla.py",
|
|
"vllm_ascend/ops/mm_encoder_attention.py",
|
|
"vllm_ascend/ops/register_custom_ops.py",
|
|
"vllm_ascend/ops/vocab_parallel_embedding.py",
|
|
"vllm_ascend/ops/weight_prefetch.py",
|
|
"vllm_ascend/spec_decode/**",
|
|
|
|
# (10)
|
|
"vllm_ascend/ops/*linear*.py",
|
|
"vllm_ascend/worker/worker.py",
|
|
"vllm_ascend/distributed/parallel_state.py",
|
|
"vllm_ascend/distributed/utils.py",
|
|
"vllm_ascend/xlite/*.py",
|
|
"vllm_ascend/patch/worker/patch_*.py",
|
|
"vllm_ascend/worker/v2/**",
|
|
"vllm_ascend/worker/npu_input_batch.py",
|
|
"vllm_ascend/ops/rotary_embedding.py",
|
|
|
|
# (11)
|
|
"vllm_ascend/ops/fused_moe/**",
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
# pycodestyle
|
|
"E",
|
|
# Pyflakes
|
|
"F",
|
|
# pyupgrade
|
|
"UP",
|
|
# flake8-bugbear
|
|
"B",
|
|
# flake8-simplify
|
|
"SIM",
|
|
# isort
|
|
"I",
|
|
# flake8-logging-format
|
|
"G",
|
|
]
|
|
ignore = [
|
|
# star imports
|
|
"F405", "F403",
|
|
# lambda expression assignment
|
|
"E731",
|
|
# zip without `strict=`
|
|
"B905",
|
|
# Loop control variable not used within loop body
|
|
"B007",
|
|
# f-string format
|
|
"UP032",
|
|
# TODO: FIE ME
|
|
"G004",
|
|
"B904",
|
|
"SIM108",
|
|
"SIM102"
|
|
]
|
|
|
|
[tool.ruff.format]
|
|
docstring-code-format = true
|