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
22e6c96f
Unverified
Commit
22e6c96f
authored
Jul 22, 2025
by
Graham King
Committed by
GitHub
Jul 22, 2025
Browse files
chore: Change vllm K8s from dynamo-run to python -m dynamo.frontend (#2055)
parent
9cfaa7be
Changes
5
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
5 additions
and
27 deletions
+5
-27
components/backends/vllm/deploy/agg.yaml
components/backends/vllm/deploy/agg.yaml
+1
-6
components/backends/vllm/deploy/agg_router.yaml
components/backends/vllm/deploy/agg_router.yaml
+1
-8
components/backends/vllm/deploy/disagg.yaml
components/backends/vllm/deploy/disagg.yaml
+1
-6
components/backends/vllm/deploy/disagg_planner.yaml
components/backends/vllm/deploy/disagg_planner.yaml
+1
-6
components/backends/vllm/deploy/disagg_router.yaml
components/backends/vllm/deploy/disagg_router.yaml
+1
-1
No files found.
components/backends/vllm/deploy/agg.yaml
View file @
22e6c96f
...
@@ -41,12 +41,7 @@ spec:
...
@@ -41,12 +41,7 @@ spec:
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir
:
/workspace/components/backends/vllm
workingDir
:
/workspace/components/backends/vllm
args
:
args
:
-
dynamo
-
"
python3
-m
dynamo.frontend
--http-port
8000"
-
run
-
in=http
-
out=dyn
-
--http-port
-
"
8000"
VllmDecodeWorker
:
VllmDecodeWorker
:
envFromSecret
:
hf-token-secret
envFromSecret
:
hf-token-secret
livenessProbe
:
livenessProbe
:
...
...
components/backends/vllm/deploy/agg_router.yaml
View file @
22e6c96f
...
@@ -41,14 +41,7 @@ spec:
...
@@ -41,14 +41,7 @@ spec:
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir
:
/workspace/components/backends/vllm
workingDir
:
/workspace/components/backends/vllm
args
:
args
:
-
dynamo
-
"
python3
-m
dynamo.frontend
--http-port
8000
--router-mode
kv"
-
run
-
in=http
-
out=dyn
-
--http-port
-
"
8000"
-
--router-mode
-
kv
VllmDecodeWorker
:
VllmDecodeWorker
:
envFromSecret
:
hf-token-secret
envFromSecret
:
hf-token-secret
livenessProbe
:
livenessProbe
:
...
...
components/backends/vllm/deploy/disagg.yaml
View file @
22e6c96f
...
@@ -41,12 +41,7 @@ spec:
...
@@ -41,12 +41,7 @@ spec:
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir
:
/workspace/components/backends/vllm
workingDir
:
/workspace/components/backends/vllm
args
:
args
:
-
dynamo
-
"
python3
-m
dynamo.frontend
--http-port
8000"
-
run
-
in=http
-
out=dyn
-
--http-port
-
"
8000"
VllmDecodeWorker
:
VllmDecodeWorker
:
dynamoNamespace
:
vllm-v1-disagg
dynamoNamespace
:
vllm-v1-disagg
envFromSecret
:
hf-token-secret
envFromSecret
:
hf-token-secret
...
...
components/backends/vllm/deploy/disagg_planner.yaml
View file @
22e6c96f
...
@@ -41,12 +41,7 @@ spec:
...
@@ -41,12 +41,7 @@ spec:
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir
:
/workspace/components/backends/vllm
workingDir
:
/workspace/components/backends/vllm
args
:
args
:
-
dynamo
-
"
python3
-m
dynamo.frontend
--http-port
8000"
-
run
-
in=http
-
out=dyn
-
--http-port
-
"
8000"
VllmDecodeWorker
:
VllmDecodeWorker
:
dynamoNamespace
:
vllm-v1-disagg-planner
dynamoNamespace
:
vllm-v1-disagg-planner
envFromSecret
:
hf-token-secret
envFromSecret
:
hf-token-secret
...
...
components/backends/vllm/deploy/disagg_router.yaml
View file @
22e6c96f
...
@@ -41,7 +41,7 @@ spec:
...
@@ -41,7 +41,7 @@ spec:
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
image
:
nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir
:
/workspace/components/backends/vllm
workingDir
:
/workspace/components/backends/vllm
args
:
args
:
-
"
python3
-m
dynamo.frontend
--http-port
80
8
0
--router-mode
kv"
-
"
python3
-m
dynamo.frontend
--http-port
80
0
0
--router-mode
kv"
VllmDecodeWorker
:
VllmDecodeWorker
:
dynamoNamespace
:
vllm-v1-disagg-router
dynamoNamespace
:
vllm-v1-disagg-router
envFromSecret
:
hf-token-secret
envFromSecret
:
hf-token-secret
...
...
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