Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
32 commits
Select commit Hold shift + click to select a range
90f02f1
format
yechenzhi May 11, 2026
80c1d78
format
yechenzhi May 12, 2026
9188c7f
format
yechenzhi May 12, 2026
70a9284
format
yechenzhi May 13, 2026
e2d04dc
format
yechenzhi May 13, 2026
5b83ffe
rollback
yechenzhi May 13, 2026
4d74dda
re organize pipelines
yechenzhi May 14, 2026
b3e211e
tests
yechenzhi May 14, 2026
34a6e8f
del sB
yechenzhi May 14, 2026
7bda128
adjust dh store side path
yechenzhi May 14, 2026
87336c7
trans and not trans tRS seperatly
yechenzhi May 14, 2026
11bb357
trans and not trans use same tRS
yechenzhi May 14, 2026
700b1a4
format
yechenzhi May 15, 2026
ddf074f
fix atol and rtol to 1e-2
yechenzhi May 16, 2026
192d3b3
dh publish earlier
yechenzhi May 16, 2026
dfbfdee
add input stage=3
yechenzhi May 17, 2026
94e4783
optimize g
yechenzhi May 17, 2026
5a10d44
fix regs
yechenzhi May 17, 2026
35866e1
mv dh to front
yechenzhi May 18, 2026
3375d27
Optimize SM90 bwd_dhu pipeline overlap and dv2 store buffering
yechenzhi May 18, 2026
3dac026
format
yechenzhi May 19, 2026
ef85210
del empty cache
yechenzhi May 19, 2026
47e62d9
format
yechenzhi May 19, 2026
bad0189
only concrete problem size to compiled kernel
yechenzhi May 19, 2026
a1aae3d
optimize gk decay way
yechenzhi May 20, 2026
9f4553b
dh tma load
yechenzhi May 20, 2026
ec18ae7
dh0 tma store
yechenzhi May 20, 2026
793d3c7
dv2 store stage
yechenzhi May 21, 2026
1c68d94
K/Q/Q multicast
yechenzhi May 22, 2026
c7a3a69
dv2
yechenzhi May 25, 2026
af1c84f
use_g
yechenzhi May 25, 2026
f550877
use_g
yechenzhi May 25, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading