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

[Model] Introduce Kimi Linear to vLLM (#27809)

Browse Source 
Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>
This commit is contained in:
Zhiyuan Li
2025-10-30 21:02:27 +08:00
committed by GitHub
parent 1994de99ea
commit 4e68cc9b6a
15 changed files with 1325 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/transformers_utils/config.py
View File

@@ -79,6 +79,7 @@ _CONFIG_REGISTRY: dict[str, type[PretrainedConfig]] = LazyConfigDict(
deepseek_v3="DeepseekV3Config",
deepseek_v32="DeepseekV3Config",
flex_olmo="FlexOlmoConfig",
kimi_linear="KimiLinearConfig",
kimi_vl="KimiVLConfig",
Llama_Nemotron_Nano_VL="Nemotron_Nano_VL_Config",
RefinedWeb="RWConfig", # For tiiuae/falcon-40b(-instruct)