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
norm
vllm
Commits
980dd4a2
Unverified
Commit
980dd4a2
authored
Oct 11, 2023
by
CHU Tianxiang
Committed by
GitHub
Oct 11, 2023
Browse files
Fix overflow in awq kernel (#1295)
Co-authored-by:
楚天翔
<
tianxiang.ctx@alibaba-inc.com
>
parent
82857368
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
csrc/quantization/awq/gemm_kernels.cu
csrc/quantization/awq/gemm_kernels.cu
+2
-2
No files found.
csrc/quantization/awq/gemm_kernels.cu
View file @
980dd4a2
...
@@ -90,7 +90,7 @@ __global__ void __launch_bounds__(64) gemm_forward_4bit_cuda_m16n128k32(int G, i
...
@@ -90,7 +90,7 @@ __global__ void __launch_bounds__(64) gemm_forward_4bit_cuda_m16n128k32(int G, i
+
(((
int
)
threadIdx
.
x
)
%
(
128
/
8
))
*
8
;
+
(((
int
)
threadIdx
.
x
)
%
(
128
/
8
))
*
8
;
half
*
C_ptr
=
C
half
*
C_ptr
=
C
+
blockIdx_z
*
M
*
OC
// blockIdz.x -> split_k dim
+
static_cast
<
long
long
>
(
blockIdx_z
)
*
M
*
OC
// blockIdz.x -> split_k dim
+
(((
int
)
blockIdx_y
)
%
j_factors1
)
*
128
+
(((
int
)
blockIdx_y
)
%
j_factors1
)
*
128
+
((
int
)
threadIdx
.
y
)
*
64
+
((
int
)
threadIdx
.
y
)
*
64
+
(((
int
)
threadIdx
.
x
)
%
4
)
*
2
;
+
(((
int
)
threadIdx
.
x
)
%
4
)
*
2
;
...
@@ -323,7 +323,7 @@ __global__ void __launch_bounds__(64) gemm_forward_4bit_cuda_m16n64k32(int G, in
...
@@ -323,7 +323,7 @@ __global__ void __launch_bounds__(64) gemm_forward_4bit_cuda_m16n64k32(int G, in
+
(((
int
)
threadIdx
.
x
)
%
(
64
/
8
))
*
8
;
+
(((
int
)
threadIdx
.
x
)
%
(
64
/
8
))
*
8
;
half
*
C_ptr
=
C
half
*
C_ptr
=
C
+
blockIdx_z
*
M
*
OC
// blockIdz.x -> split_k dim
+
static_cast
<
long
long
>
(
blockIdx_z
)
*
M
*
OC
// blockIdz.x -> split_k dim
+
(((
int
)
blockIdx_y
)
%
j_factors1
)
*
64
+
(((
int
)
blockIdx_y
)
%
j_factors1
)
*
64
+
((
int
)
threadIdx
.
y
)
*
32
+
((
int
)
threadIdx
.
y
)
*
32
+
(((
int
)
threadIdx
.
x
)
%
4
)
*
2
;
+
(((
int
)
threadIdx
.
x
)
%
4
)
*
2
;
...
...
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
楚天翔 <tianxiang.ctx@alibaba-inc.com>楚天翔 <tianxiang.ctx@alibaba-inc.com>