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
bitsandbytes
Commits
45dc1983
Commit
45dc1983
authored
Sep 18, 2022
by
justheuristic
Browse files
cast properly
parent
702cc720
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
2 deletions
+1
-2
bitsandbytes/autograd/_functions.py
bitsandbytes/autograd/_functions.py
+1
-2
No files found.
bitsandbytes/autograd/_functions.py
View file @
45dc1983
...
@@ -294,7 +294,7 @@ class MatMul8bitLt(torch.autograd.Function):
...
@@ -294,7 +294,7 @@ class MatMul8bitLt(torch.autograd.Function):
(
outliers
*
state
.
SCB
.
view
(
-
1
,
1
)
/
127.0
)
(
outliers
*
state
.
SCB
.
view
(
-
1
,
1
)
/
127.0
)
.
t
()
.
t
()
.
contiguous
()
.
contiguous
()
.
half
(
)
.
to
(
B
.
dtype
)
)
)
CA
[:,
state
.
idx
.
long
()]
=
0
CA
[:,
state
.
idx
.
long
()]
=
0
CAt
[:,
state
.
idx
.
long
()]
=
0
CAt
[:,
state
.
idx
.
long
()]
=
0
...
@@ -321,7 +321,6 @@ class MatMul8bitLt(torch.autograd.Function):
...
@@ -321,7 +321,6 @@ class MatMul8bitLt(torch.autograd.Function):
# 4. Mixed-precision decomposition matmul
# 4. Mixed-precision decomposition matmul
if
coo_tensorA
is
not
None
and
subA
is
not
None
:
if
coo_tensorA
is
not
None
and
subA
is
not
None
:
assert
subA
.
dtype
==
state
.
subB
.
dtype
,
(
subA
.
dtype
,
state
.
subB
.
dtype
)
output
+=
torch
.
matmul
(
subA
,
state
.
subB
)
output
+=
torch
.
matmul
(
subA
,
state
.
subB
)
# 5. Save state
# 5. Save state
...
...
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