Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
fac4e969
Unverified
Commit
fac4e969
authored
Feb 12, 2026
by
Hashem Hashemi
Committed by
GitHub
Feb 12, 2026
Browse files
small adjustment to wvSplitKrc (#34410)
Signed-off-by:
Hashem Hashemi
<
hashem.hashemi@amd.com
>
parent
6d4e27ce
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
2 deletions
+1
-2
csrc/rocm/skinny_gemms.cu
csrc/rocm/skinny_gemms.cu
+1
-2
No files found.
csrc/rocm/skinny_gemms.cu
View file @
fac4e969
...
@@ -1568,8 +1568,7 @@ __global__ void __launch_bounds__(WvPrGrp* THRDS)
...
@@ -1568,8 +1568,7 @@ __global__ void __launch_bounds__(WvPrGrp* THRDS)
{
{
#endif
#endif
unsigned
int
kOff
=
k
+
(
thrd
*
A_CHUNK
);
unsigned
int
kOff
=
k
+
(
thrd
*
A_CHUNK
);
unsigned
int
kOffcp
=
unsigned
int
kOffcp
=
min__
(
K
-
A_CHUNK
,
k_str
+
kOff
);
k_str
+
kOff
;
// min__(K - A_CHUNK, k_str + kOff);
for
(
unsigned
int
n
=
0
;
n
<
N
;
n
+=
CHUNKK
*
sprdN
)
{
for
(
unsigned
int
n
=
0
;
n
<
N
;
n
+=
CHUNKK
*
sprdN
)
{
__builtin_amdgcn_global_load_lds
(
__builtin_amdgcn_global_load_lds
(
(
int
*
)(
&
A
[
min__
(
(
int
*
)(
&
A
[
min__
(
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment