[CUDA] upgrade cutlass to 3.5.0 #20940
Add /Zc:__cplusplus
dd964cb0
update cutlass
e31edf74
Add code to use batch hook
4ee7731a
update cgmanifest
94a3b2e9
tianleiwu
marked this pull request as draft 1 year ago
snnn
commented
on 2024-06-05
limit max head size = 1024
fd89bb95
fix linux build
be8f3c65
use GQAToBatchHook
02886c2e
cutlass patch to fix hrsqrt not found for SM<53
0f460d1d
suppress TRT deprecated warnings
ed63a78c
undo to_batch_hook
274862be
suppress trt deprecate warning and clean up
8d5c4c08
tianleiwu
marked this pull request as ready for review 1 year ago
snnn
dismissed these changes
on 2024-06-10
address review feedback
a02c612d
snnn
dismissed their stale review
1 year ago
fix more 4996 warnings
415c5e10
tianleiwu
force pushed
from
6adb2cdd
to
415c5e10
1 year ago
wangyems
approved these changes
on 2024-06-11
snnn
approved these changes
on 2024-06-11
faxu
approved these changes
on 2024-06-11
tianleiwu
merged
b3fc9b5a
into main 1 year ago
tianleiwu
deleted the tlwu/fix_cutlass_msvc_build_error branch 1 year ago
Assignees
No one assigned
Labels
ep:CUDA
ep:TensorRT