Add pydocstyle to the ruff rules (#52136)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-16 16:44:29 +00:00
committed by GitHub
co-authored by Claude Opus 5
parent 804e5377aa
commit 8c1557a79c
2002 changed files with 15024 additions and 14269 deletions
@@ -23,7 +23,7 @@ DTYPES = [torch.float32]
def reference_lightning_attention(q, k, v, ed, block_size, kv_history):
"""Reference implementation of lightning attention core algorithm
"""Reference implementation of lightning attention core algorithm.
The difference from the main implementation is that this processes
each step sequentially, instead of using parallelized triton kernels
@@ -72,7 +72,7 @@ def reference_lightning_attention(q, k, v, ed, block_size, kv_history):
def reference_linear_decode(q, k, v, kv_caches, slope_rate, slot_idx):
"""Reference implementation: linear attention decode function"""
"""Reference implementation: linear attention decode function."""
B, H, _, D = q.shape
output = torch.zeros(B, H * D, dtype=q.dtype, device=q.device)