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
+8 -1
View File
@@ -76,7 +76,8 @@ class EncoderCudaGraphManager:
model: SupportsEncoderCudaGraph,
):
"""Initialize CUDA graph manager with provided token budgets
and max batch size."""
and max batch size.
"""
self.vllm_config = vllm_config
self.device = device
self.dtype = dtype
@@ -351,6 +352,7 @@ class EncoderCudaGraphManager:
Returns:
Token budget if found, None if no fitting budget.
"""
budgets = budgets if budgets is not None else self.token_budgets
for budget in budgets:
@@ -411,8 +413,11 @@ class EncoderCudaGraphManager:
mm_kwargs: Multimodal inputs for the batch.
token_budget: Token budget to use.
path: Configured encoder path.
axis_keys: Resolved capture-axis keys for this batch.
Returns:
Encoder outputs, or None if graph not captured.
"""
graph_set = self._get_graph_set(path)
num_items = len(self._get_item_specs(mm_kwargs))
@@ -562,6 +567,7 @@ class EncoderCudaGraphManager:
images_per_rank: Number of items per rank.
max_output_tokens_per_rank: Max output tokens across all ranks
(for padding during all_gather).
"""
tp_size = get_tensor_model_parallel_world_size()
current_rank = get_tensor_model_parallel_rank()
@@ -687,6 +693,7 @@ class EncoderCudaGraphManager:
Returns:
List of encoder outputs (one per item).
"""
if self.use_dp:
per_item_out_tokens = self._get_per_item_out_tokens(mm_kwargs)