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
c26e6fb8
Unverified
Commit
c26e6fb8
authored
Dec 16, 2025
by
atchernych
Committed by
GitHub
Dec 16, 2025
Browse files
feat: Update GAIE recipe (#4761)
Signed-off-by:
Anna Tchernych
<
atchernych@nvidia.com
>
parent
6da23fcf
Changes
4
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
764 additions
and
2 deletions
+764
-2
deploy/inference-gateway/build-epp-dynamo.sh
deploy/inference-gateway/build-epp-dynamo.sh
+1
-1
deploy/inference-gateway/epp-patches/v0.8.0/gaie.patch
deploy/inference-gateway/epp-patches/v0.8.0/gaie.patch
+761
-0
recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/http-route.yaml
...ama-3-70b/vllm/agg/gaie/k8s-manifests/epp/http-route.yaml
+1
-0
recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/model/inference-pool.yaml
...70b/vllm/agg/gaie/k8s-manifests/model/inference-pool.yaml
+1
-1
No files found.
deploy/inference-gateway/build-epp-dynamo.sh
View file @
c26e6fb8
...
...
@@ -83,7 +83,7 @@ echo " Docker: ${GAIE_DIR}/Dockerfile.epp"
echo
"Applying Dynamo patch..."
cd
"
${
GAIE_DIR
}
"
PATCH_FILE
=
"
${
DYNAMO_DIR
}
/deploy/inference-gateway/epp-patches/v0.
5.1-2/epp-v0.5.1-dyn2
.patch"
PATCH_FILE
=
"
${
DYNAMO_DIR
}
/deploy/inference-gateway/epp-patches/v0.
8.0/gaie
.patch"
if
[[
-f
"
${
PATCH_FILE
}
"
]]
;
then
if
git apply
--check
"
${
PATCH_FILE
}
"
2>/dev/null
;
then
git apply
"
${
PATCH_FILE
}
"
...
...
deploy/inference-gateway/epp-patches/v0.8.0/gaie.patch
0 → 100644
View file @
c26e6fb8
This diff is collapsed.
Click to expand it.
recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/http-route.yaml
View file @
c26e6fb8
...
...
@@ -24,6 +24,7 @@ spec:
-
group
:
gateway.networking.k8s.io
kind
:
Gateway
name
:
inference-gateway
namespace
:
kgateway-system
rules
:
-
backendRefs
:
-
group
:
inference.networking.x-k8s.io
...
...
recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/model/inference-pool.yaml
View file @
c26e6fb8
...
...
@@ -21,7 +21,7 @@ metadata:
spec
:
targetPortNumber
:
8000
selector
:
nvidia.com/dynamo-component
:
F
rontend
nvidia.com/dynamo-component
-type
:
f
rontend
extensionRef
:
failureMode
:
FailOpen
group
:
"
"
...
...
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