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
07eb6f19
"vscode:/vscode.git/clone" did not exist on "ef9baee3c52f719df64a646db72b6c4ede8a29a0"
Unverified
Commit
07eb6f19
authored
Jul 19, 2024
by
youkaichao
Committed by
GitHub
Jul 19, 2024
Browse files
[bugfix][distributed] fix multi-node bug for shared memory (#6597)
parent
f0bbfaf9
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
2 deletions
+8
-2
vllm/distributed/device_communicators/shm_broadcast.py
vllm/distributed/device_communicators/shm_broadcast.py
+8
-2
No files found.
vllm/distributed/device_communicators/shm_broadcast.py
View file @
07eb6f19
...
...
@@ -108,8 +108,14 @@ class ShmRingBuffer:
# created by the process. The following patch is a workaround.
with
patch
(
"multiprocessing.resource_tracker.register"
,
lambda
*
args
,
**
kwargs
:
None
):
self
.
shared_memory
=
shared_memory
.
SharedMemory
(
name
=
name
)
assert
self
.
shared_memory
.
size
==
self
.
total_bytes_of_buffer
try
:
self
.
shared_memory
=
shared_memory
.
SharedMemory
(
name
=
name
)
assert
self
.
shared_memory
.
size
==
self
.
total_bytes_of_buffer
# noqa
except
FileNotFoundError
:
# we might deserialize the object in a different node
# in this case, this object is not used,
# and we should suppress the error
pass
def
__reduce__
(
self
):
return
(
...
...
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