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
change
sglang
Commits
0e78c63c
Unverified
Commit
0e78c63c
authored
Sep 05, 2025
by
Yineng Zhang
Committed by
GitHub
Sep 05, 2025
Browse files
Revert "[1/N][Bug] Fix w4afp8 MoE NaN issue (sgl-kernel) (#9953)" (#10097)
parent
1a3d6f31
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
sgl-kernel/csrc/moe/cutlass_moe/w4a8/w4a8_grouped_mm_c3x.cuh
sgl-kernel/csrc/moe/cutlass_moe/w4a8/w4a8_grouped_mm_c3x.cuh
+2
-2
No files found.
sgl-kernel/csrc/moe/cutlass_moe/w4a8/w4a8_grouped_mm_c3x.cuh
View file @
0e78c63c
...
@@ -41,8 +41,8 @@ using MmaType = cutlass::float_e4m3_t; // FP8 e4m3 type
...
@@ -41,8 +41,8 @@ using MmaType = cutlass::float_e4m3_t; // FP8 e4m3 type
using
QuantType
=
cutlass
::
int4b_t
;
// 4-bit integer type
using
QuantType
=
cutlass
::
int4b_t
;
// 4-bit integer type
using
ElementAccumulator
=
float
;
// Accumulator type
using
ElementAccumulator
=
float
;
// Accumulator type
using
ElementScale
=
cutlass
::
bfloat16_t
;
// Scale type
using
ElementScale
=
cutlass
::
bfloat16_t
;
// Scale type
using
ElementC
=
cutlass
::
bfloat16
_t
;
//
O
utput type
using
ElementC
=
cutlass
::
half
_t
;
//
Default o
utput type
(FP16)
using
ElementD
=
ElementC
;
//
O
utput type
using
ElementD
=
ElementC
;
//
Default o
utput type
(FP16)
using
ProblemShape
=
cutlass
::
gemm
::
GroupProblemShape
<
Shape
<
int
,
int
,
int
>>
;
using
ProblemShape
=
cutlass
::
gemm
::
GroupProblemShape
<
Shape
<
int
,
int
,
int
>>
;
// Architecture-specific configurations
// Architecture-specific configurations
...
...
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