[Core][Performance] Add XGrammar support for guided decoding and set it as default · vllm-project/vllm@b29dfb3

Triggered via pull request November 29, 2024 23:45

aarnphm

opened #10785

aarnphm:feat/xgrammar

Status Failure

Total duration 23s

Artifacts –

ruff.yml

on: pull_request

Matrix: ruff

10 errors

Ruff (E501): vllm/config.py#L2016

vllm/config.py:2016:81: E501 Line too long (87 > 80)

Ruff (F401): vllm/model_executor/guided_decoding/__init__.py#L3

vllm/model_executor/guided_decoding/__init__.py:3:30: F401 `typing.Any` imported but unused

Ruff (UP007): vllm/model_executor/guided_decoding/__init__.py#L14

vllm/model_executor/guided_decoding/__init__.py:14:39: UP007 Use `X | Y` for type annotations

Ruff (E501): vllm/model_executor/guided_decoding/__init__.py#L28

vllm/model_executor/guided_decoding/__init__.py:28:81: E501 Line too long (125 > 80)

Ruff (UP007): vllm/model_executor/guided_decoding/__init__.py#L39

vllm/model_executor/guided_decoding/__init__.py:39:39: UP007 Use `X | Y` for type annotations

Ruff (E501): vllm/model_executor/guided_decoding/__init__.py#L53

vllm/model_executor/guided_decoding/__init__.py:53:81: E501 Line too long (125 > 80)

Ruff (E401): vllm/model_executor/guided_decoding/xgrammar_decoding.py#L3

vllm/model_executor/guided_decoding/xgrammar_decoding.py:3:1: E401 Multiple imports on one line

Ruff (E501): vllm/model_executor/guided_decoding/xgrammar_decoding.py#L28

vllm/model_executor/guided_decoding/xgrammar_decoding.py:28:81: E501 Line too long (109 > 80)

Ruff (UP007): vllm/model_executor/guided_decoding/xgrammar_decoding.py#L36

vllm/model_executor/guided_decoding/xgrammar_decoding.py:36:15: UP007 Use `X | Y` for type annotations

Ruff (UP007): vllm/model_executor/guided_decoding/xgrammar_decoding.py#L37

vllm/model_executor/guided_decoding/xgrammar_decoding.py:37:18: UP007 Use `X | Y` for type annotations