biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574)

Browse Source 
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
This commit is contained in:
Kata Coder
2026-02-21 13:01:40 +09:00
committed by GitHub
parent 11be2c74dc
commit 5719a4e4e6
10 changed files with 532 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/transformers_utils/config.py
View File

@@ -76,6 +76,7 @@ _CONFIG_REGISTRY: dict[str, type[PretrainedConfig]] = LazyConfigDict(
chatglm="ChatGLMConfig",
colqwen3="ColQwen3Config",
ops_colqwen3="OpsColQwen3Config",
qwen3_vl_nemotron_embed="Qwen3VLNemotronEmbedConfig",
deepseek_vl_v2="DeepseekVLV2Config",
deepseek_v32="DeepseekV3Config",
flex_olmo="FlexOlmoConfig",