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
dynamo
Commits
31f31e8e
Unverified
Commit
31f31e8e
authored
Dec 11, 2025
by
Ziqi Fan
Committed by
GitHub
Dec 11, 2025
Browse files
fix: remove small --gpu-memory-utilization to avoid OOM due to vllm upgrade (#4899)
Signed-off-by:
Ziqi Fan
<
ziqif@nvidia.com
>
parent
5e96c9a8
Changes
3
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
0 additions
and
10 deletions
+0
-10
examples/backends/vllm/deploy/agg_kvbm.yaml
examples/backends/vllm/deploy/agg_kvbm.yaml
+0
-2
examples/backends/vllm/deploy/disagg_kvbm.yaml
examples/backends/vllm/deploy/disagg_kvbm.yaml
+0
-4
examples/backends/vllm/deploy/disagg_kvbm_2p2d.yaml
examples/backends/vllm/deploy/disagg_kvbm_2p2d.yaml
+0
-4
No files found.
examples/backends/vllm/deploy/agg_kvbm.yaml
View file @
31f31e8e
...
@@ -40,8 +40,6 @@ spec:
...
@@ -40,8 +40,6 @@ spec:
args
:
args
:
-
--model
-
--model
-
Qwen/Qwen3-8B
-
Qwen/Qwen3-8B
-
--gpu-memory-utilization
-
"
0.45"
-
--max-model-len
-
--max-model-len
-
"
32000"
-
"
32000"
-
--enforce-eager
-
--enforce-eager
...
...
examples/backends/vllm/deploy/disagg_kvbm.yaml
View file @
31f31e8e
...
@@ -33,8 +33,6 @@ spec:
...
@@ -33,8 +33,6 @@ spec:
args
:
args
:
-
--model
-
--model
-
Qwen/Qwen3-8B
-
Qwen/Qwen3-8B
-
--gpu-memory-utilization
-
"
0.3"
-
--max-model-len
-
--max-model-len
-
"
32000"
-
"
32000"
-
--enforce-eager
-
--enforce-eager
...
@@ -65,8 +63,6 @@ spec:
...
@@ -65,8 +63,6 @@ spec:
-
--model
-
--model
-
Qwen/Qwen3-8B
-
Qwen/Qwen3-8B
-
--is-prefill-worker
-
--is-prefill-worker
-
--gpu-memory-utilization
-
"
0.3"
-
--max-model-len
-
--max-model-len
-
"
32000"
-
"
32000"
-
--enforce-eager
-
--enforce-eager
...
...
examples/backends/vllm/deploy/disagg_kvbm_2p2d.yaml
View file @
31f31e8e
...
@@ -33,8 +33,6 @@ spec:
...
@@ -33,8 +33,6 @@ spec:
args
:
args
:
-
--model
-
--model
-
Qwen/Qwen3-8B
-
Qwen/Qwen3-8B
-
--gpu-memory-utilization
-
"
0.3"
-
--max-model-len
-
--max-model-len
-
"
32000"
-
"
32000"
-
--enforce-eager
-
--enforce-eager
...
@@ -65,8 +63,6 @@ spec:
...
@@ -65,8 +63,6 @@ spec:
-
--model
-
--model
-
Qwen/Qwen3-8B
-
Qwen/Qwen3-8B
-
--is-prefill-worker
-
--is-prefill-worker
-
--gpu-memory-utilization
-
"
0.3"
-
--max-model-len
-
--max-model-len
-
"
32000"
-
"
32000"
-
--enforce-eager
-
--enforce-eager
...
...
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