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
+2 -2
View File
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
ColQwen3.5 late interaction model for multi-modal retrieval and reranking.
"""ColQwen3.5 late interaction model for multi-modal retrieval and reranking.
ColQwen3.5 extends Qwen3.5 with a ColBERT-style late interaction head,
producing per-token embeddings for both text and image inputs. It uses
@@ -128,6 +127,7 @@ class ColQwen3_5Model(
Attributes:
custom_text_proj: Linear projection from hidden_size to embed_dim.
This is passed to the pooler as pooler.head.projector.
"""
# Mark this as a pooling model so vLLM routes to pooler path