[Model] Support pooling models#3122

Open

lianyiibo wants to merge 14 commits intovllm-project:mainfrom

lianyiibo:pooling_support

Commits on Dec 6, 2025

Support pooling models with aclgraph

lianyiibo
authored and
MengqingCao
committed
Add pooling attention branch

lianyiibo
authored and
MengqingCao
committed
Some fixes
MengqingCao
committed
fix pooling mask
MengqingCao
committed
remove issue link

lianyiibo
authored and
MengqingCao
committed
reduce cudagraph_capture_sizes to speed up CI
MengqingCao
committed
add a lightly ci
MengqingCao
committed
remove redundant code
MengqingCao
committed
fix issue included by rebase
MengqingCao
committed
remove redundant code
MengqingCao
committed

Commits on Dec 8, 2025

Commits on Dec 9, 2025