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
cdeec2e6
Unverified
Commit
cdeec2e6
authored
Nov 19, 2025
by
Julien Denize
Committed by
GitHub
Nov 19, 2025
Browse files
[BugFix] Ray with multiple nodes (#28873)
Signed-off-by:
Julien Denize
<
julien.denize@mistral.ai
>
parent
1607e664
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
8 deletions
+8
-8
vllm/v1/worker/gpu_worker.py
vllm/v1/worker/gpu_worker.py
+8
-8
No files found.
vllm/v1/worker/gpu_worker.py
View file @
cdeec2e6
...
@@ -209,8 +209,8 @@ class Worker(WorkerBase):
...
@@ -209,8 +209,8 @@ class Worker(WorkerBase):
torch
.
cuda
.
device_count
()
if
torch
.
cuda
.
is_available
()
else
0
torch
.
cuda
.
device_count
()
if
torch
.
cuda
.
is_available
()
else
0
)
)
assert
self
.
parallel_config
.
local_world_size
<=
visible_device_count
,
(
assert
self
.
parallel_config
.
local_world_size
<=
visible_device_count
,
(
f
"local_world_size (
{
self
.
parallel_config
.
local_world_size
}
) must
be
"
f
"local_world_size (
{
self
.
parallel_config
.
local_world_size
}
) must "
f
"
less than or equal to the number of visible devices "
f
"be
less than or equal to the number of visible devices "
f
"(
{
visible_device_count
}
)."
f
"(
{
visible_device_count
}
)."
)
)
self
.
device
=
torch
.
device
(
f
"cuda:
{
self
.
local_rank
}
"
)
self
.
device
=
torch
.
device
(
f
"cuda:
{
self
.
local_rank
}
"
)
...
...
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