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
9b87a579
Unverified
Commit
9b87a579
authored
Mar 17, 2025
by
Yan Ma
Committed by
GitHub
Mar 17, 2025
Browse files
[Misc][XPU] Use None as device capacity for XPU (#14932)
Signed-off-by:
yan ma
<
yan.ma@intel.com
>
parent
b539222d
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
4 deletions
+5
-4
vllm/platforms/xpu.py
vllm/platforms/xpu.py
+5
-4
No files found.
vllm/platforms/xpu.py
View file @
9b87a579
...
@@ -37,10 +37,11 @@ class XPUPlatform(Platform):
...
@@ -37,10 +37,11 @@ class XPUPlatform(Platform):
return
"vllm.attention.backends.ipex_attn.IpexAttnBackend"
return
"vllm.attention.backends.ipex_attn.IpexAttnBackend"
@
staticmethod
@
staticmethod
def
get_device_capability
(
device_id
:
int
=
0
)
->
DeviceCapability
:
def
get_device_capability
(
major
,
minor
,
*
_
=
torch
.
xpu
.
get_device_capability
(
device_id
:
int
=
0
)
->
Optional
[
DeviceCapability
]:
device_id
)[
'version'
].
split
(
'.'
)
# capacity format differs from cuda's and will cause unexpected
return
DeviceCapability
(
major
=
int
(
major
),
minor
=
int
(
minor
))
# failure, so use None directly
return
None
@
staticmethod
@
staticmethod
def
get_device_name
(
device_id
:
int
=
0
)
->
str
:
def
get_device_name
(
device_id
:
int
=
0
)
->
str
:
...
...
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