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
OpenDAS
TransformerEngine
Commits
e704bbc8
Commit
e704bbc8
authored
Jun 18, 2025
by
wenjh
Browse files
Fix build error
Signed-off-by:
wenjh
<
wenjh@sugon.com
>
parent
331f2fc4
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu
...e/common/transpose/quantize_transpose_vector_blockwise.cu
+2
-2
No files found.
transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu
View file @
e704bbc8
...
...
@@ -505,7 +505,7 @@ __global__ void __launch_bounds__(kThreadsPerBlock) block_scaled_1d_cast_transpo
amax
=
warp_reduce_max
<
kThreadsPerWarp
>
(
amax
);
constexpr
int
lane_zero
=
0
;
#ifdef __HIP_PLATFORM_AMD__
amax
=
__shfl_sync
(
0xFFFFFFFF
,
amax
,
lane_zero
,
kThreadsPerWarp
);
amax
=
__shfl_sync
(
(
unsigned
long
long
)(
0xFFFFFFFF
)
,
amax
,
lane_zero
,
kThreadsPerWarp
);
#else
amax
=
__shfl_sync
(
0xFFFFFFFF
,
amax
,
lane_zero
);
#endif
...
...
@@ -895,7 +895,7 @@ __global__ void __launch_bounds__(kThreadsPerBlock) block_scaled_1d_cast_transpo
amax
=
warp_reduce_max
<
kThreadsPerWarp
>
(
amax
);
constexpr
int
lane_zero
=
0
;
#ifdef __HIP_PLATFORM_AMD__
amax
=
__shfl_sync
(
0xFFFFFFFF
,
amax
,
lane_zero
,
kThreadsPerWarp
);
amax
=
__shfl_sync
(
(
unsigned
long
long
)(
0xFFFFFFFF
)
,
amax
,
lane_zero
,
kThreadsPerWarp
);
#else
amax
=
__shfl_sync
(
0xFFFFFFFF
,
amax
,
lane_zero
);
#endif
...
...
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