Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
composable_kernel_ROCM
Repository
Branches
Overview
Active
Stale
All
ck-flex
4007289a
·
copy over fmha example
·
Feb 12, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
lwpck-2840
67204577
·
fix clang format
·
Feb 12, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
lwpck-2846
1fc2babd
·
add -Wno-unique-object-duplication compiler option
·
Feb 12, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
amd/dev/jruan/norm_perf
28f93c95
·
add layernorm
·
Feb 12, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
ck_tile/gemm_compute_v4
1160b994
·
sync with develop
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
pytorch_release_2.6
60c7f662
·
Make sure we call __hneg with half to remove ambigios error (#1736)
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
mtgu/dev/gemm_fp8xint4_Bpreshuffle
e4d307f8
·
Modify the tile size as 256, 128x128x128. function pass.
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
jim/ck_tile/fa_bwd_v3
41459498
·
remove code
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
fmoe_sort_porting
a6b9d13a
·
remod
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
mtgu/dev/gemm_fp8xint4_Bpreshuffle_static2static
2d256913
·
modified the tile size to 256, 128x128x128.
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
muozturk_streamk_reduction_fix
730ec369
·
update
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
barkocot/lwpck-2637-dev3
0328b06e
·
fixes
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
barkocot/lwpck-2810
59ac6d73
·
Add ngchw grouped conv bwd wei instances for numgroups=1
·
Feb 13, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
feiw/dev/flatmm
e889d086
·
save 51
·
Feb 14, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
dev/ck_moe_gemm_output_sorting
84b27d75
·
merge max_token_id and fix err
·
Feb 14, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
dev/ck_moe_gemm_hotfix
db53dba4
·
hotfix:gemm1 use real tokens and gemm2 ok
·
Feb 14, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
dev/ck_moe_gemm
56cc306d
·
fix perf calc
·
Feb 15, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
barkocot/lwpck-1919
9f65d608
·
[CK TILE] Gemm pk_int4_t permute B
·
Feb 16, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
update_cka8w8_uc
4b98b4f4
·
add the 16x16 mfma instances
·
Feb 17, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
mtgu/dev/ck_moe_int4
837d9056
·
Added b preshuffle pipeline v3 support.
·
Feb 17, 2025
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
Prev
1
…
9
10
11
12
13
14
Next