[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-16 10:57:24 -07:00
committed by GitHub
co-authored by Claude Opus 5
parent 1085b64425
commit 651a88c09a
693 changed files with 2088 additions and 4171 deletions
@@ -134,8 +134,7 @@ def test_flash_attn_registers_warmup_only_for_fa4(
def test_flash_attn_prefill_backend_signature_accepts_fused_kwargs():
"""run_prefill_new_tokens must accept out/output_scale so the direct
(non-**kwargs) call in forward_mha type- and runtime-checks.
"""
(non-**kwargs) call in forward_mha type- and runtime-checks."""
import inspect
params = inspect.signature(
@@ -151,8 +150,7 @@ def test_flash_attn_prefill_backend_signature_accepts_fused_kwargs():
def test_mla_impl_forward_mha_accepts_output_scale():
"""The abstract MLA impl forward_mha must carry output_scale so every
override (and the unconditional forward_impl call) stays compatible.
"""
override (and the unconditional forward_impl call) stays compatible."""
import inspect
from vllm.v1.attention.backend import MLAAttentionImpl
@@ -179,8 +177,7 @@ _FUSED_FP8_SKIP = _fused_fp8_skip_reason()
def test_fa4_fused_fp8_output_matches_post_quant(default_vllm_config):
"""FA4's fused FP8 write (output_scale, flash-attention#135) must match the
bf16-attention + standalone static-FP8-quant path it replaces, since
production uses the same output_scale for both.
"""
production uses the same output_scale for both."""
from vllm.model_executor.layers.quantization.input_quant_fp8 import QuantFP8
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
from vllm.platforms import current_platform