43df2cb2fc
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `tests/e2e/310p/multicard/test_vl_model_multicard.py` |
| `tests/e2e/310p/singlecard/test_vl_model_singlecard.py` |
| `tests/e2e/310p/test_utils.py` |
| `tests/e2e/conftest.py` |
| `tests/e2e/model_utils.py` |
| `tests/e2e/models/conftest.py` |
| `tests/e2e/models/test_lm_eval_correctness.py` |
| `tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py` |
| `tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py` |
| `tests/e2e/multicard/2-cards/test_data_parallel.py` |
| `tests/e2e/multicard/2-cards/test_disaggregated_encoder.py` |
| `tests/e2e/multicard/2-cards/test_expert_parallel.py` |
| `tests/e2e/multicard/2-cards/test_external_launcher.py` |
| `tests/e2e/multicard/2-cards/test_full_graph_mode.py` |
| `tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py` |
| `tests/e2e/multicard/2-cards/test_offline_inference_distributed.py` |
| `tests/e2e/multicard/2-cards/test_offline_weight_load.py` |
| `tests/e2e/multicard/2-cards/test_pipeline_parallel.py` |
| `tests/e2e/multicard/2-cards/test_prefix_caching.py` |
| `tests/e2e/multicard/2-cards/test_quantization.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe_routing_replay.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_performance.py` |
| `tests/e2e/multicard/2-cards/test_shared_expert_dp.py` |
| `tests/e2e/multicard/2-cards/test_single_request_aclgraph.py` |
| `tests/e2e/multicard/2-cards/test_sp_pass.py` |
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.15.0
- vLLM main:
9562912cea
Signed-off-by: MrZ20 <2609716663@qq.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
114 lines
2.4 KiB
TOML
114 lines
2.4 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 120 characters per line
|
|
line-length = 120
|
|
# Folder to be modified
|
|
exclude = [
|
|
# Batch (1)
|
|
# "tests/e2e/__init__.py",
|
|
# "tests/e2e/310p/",
|
|
# "tests/e2e/conftest.py",
|
|
# "tests/e2e/doctests/",
|
|
# "tests/e2e/model_utils.py",
|
|
# "tests/e2e/models/",
|
|
# "tests/e2e/multicard/2-cards/",
|
|
|
|
# Batch (2)
|
|
"tests/e2e/multicard/4-cards/",
|
|
"tests/e2e/nightly/multi_node/",
|
|
"tests/e2e/singlecard/pooling/",
|
|
"tests/e2e/singlecard/spec_decode/",
|
|
"tests/e2e/utils.py",
|
|
"tests/e2e/vllm_interface/",
|
|
"tests/e2e/weekly/",
|
|
|
|
# Batch (3)
|
|
"tests/e2e/nightly/single_node/",
|
|
|
|
"tests/ut/",
|
|
]
|
|
|
|
[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
|