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
22e718ff
Unverified
Commit
22e718ff
authored
Aug 02, 2024
by
Rui Qiao
Committed by
GitHub
Aug 02, 2024
Browse files
[Misc] Revive to use loopback address for driver IP (#7091)
Signed-off-by:
Rui Qiao
<
ruisearch42@gmail.com
>
parent
05308891
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
10 additions
and
0 deletions
+10
-0
vllm/executor/ray_gpu_executor.py
vllm/executor/ray_gpu_executor.py
+10
-0
No files found.
vllm/executor/ray_gpu_executor.py
View file @
22e718ff
...
@@ -216,6 +216,16 @@ class RayGPUExecutor(DistributedGPUExecutor):
...
@@ -216,6 +216,16 @@ class RayGPUExecutor(DistributedGPUExecutor):
self
.
_run_workers
(
"update_environment_variables"
,
self
.
_run_workers
(
"update_environment_variables"
,
all_args
=
all_args_to_update_environment_variables
)
all_args
=
all_args_to_update_environment_variables
)
if
len
(
node_gpus
)
==
1
:
# in single node case, we don't need to get the IP address.
# the loopback address is sufficient
# NOTE: a node may have several IP addresses, one for each
# network interface. `get_ip()` might return any of them,
# while they might not work for communication inside the node
# if the network setup is complicated. Using the loopback address
# solves this issue, as it always works for communication inside
# the node.
driver_ip
=
"127.0.0.1"
distributed_init_method
=
get_distributed_init_method
(
distributed_init_method
=
get_distributed_init_method
(
driver_ip
,
get_open_port
())
driver_ip
,
get_open_port
())
...
...
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