[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
+1 -2
View File
@@ -745,8 +745,7 @@ class MultiHeadLatentAttention(nn.Module, AttentionLayerBase):
slot_mapping: torch.Tensor,
) -> torch.Tensor:
"""Fused decode query-concat + latent cache insert, dispatched by cache
dtype (same policy as prefill: fp8 cache -> fp8 query).
"""
dtype (same policy as prefill: fp8 cache -> fp8 query)."""
if self.kv_cache_dtype == "fp8_ds_mla":
cache = self.kv_cache
if cache.dtype != torch.uint8: