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:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
ColQwen3 late interaction model for multi-modal retrieval and reranking.
|
||||
"""ColQwen3 late interaction model for multi-modal retrieval and reranking.
|
||||
|
||||
ColQwen3 extends Qwen3-VL with a ColBERT-style late interaction head,
|
||||
producing per-token embeddings for both text and image inputs. It uses
|
||||
@@ -131,6 +130,7 @@ class ColQwen3Model(Qwen3VLForConditionalGeneration, SupportsLateInteraction):
|
||||
|
||||
Attributes:
|
||||
custom_text_proj: Linear projection from hidden_size to embed_dim
|
||||
|
||||
"""
|
||||
|
||||
# Mark this as a pooling model so vLLM routes to pooler path
|
||||
|
||||
Reference in New Issue
Block a user