Skip to content

change disaggragation to disaggregation #793

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
volcano-sh-bot merged 1 commit into from
Mar 2, 2026
Merged

change disaggragation to disaggregation #793

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 ...ModelServer-ds1.5b-pd-disaggragation.yaml → ...ModelServer-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion docs/kthena/docs/user-guide/router-routing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,7 +294,7 @@ spec:
4. Prefill runs on prefill instance; decode runs on decode instance, with KV state exchanged between them (configure `kvConnector` for nixl/mooncake when needed)
5. Response returned to client

**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggragation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggragation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml).
**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggregation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggregation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml).

---

Expand Down
0 ...ModelServer-ds1.5b-pd-disaggragation.yaml → ...ModelServer-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion docs/kthena/versioned_docs/version-v0.1.0/user-guide/router-routing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,7 +294,7 @@ spec:
4. Prefill runs on prefill instance; decode runs on decode instance, with KV state exchanged between them (configure `kvConnector` for nixl/mooncake when needed)
5. Response returned to client

**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggragation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggragation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml).
**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggregation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggregation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml).

---

Expand Down
0 ...ModelServer-ds1.5b-pd-disaggragation.yaml → ...ModelServer-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion docs/kthena/versioned_docs/version-v0.2.0/user-guide/router-routing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -293,7 +293,7 @@ spec:
4. Prefill runs on prefill instance; decode runs on decode instance, with KV state exchanged between them (configure `kvConnector` for nixl/mooncake when needed)
5. Response returned to client

**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggragation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggragation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml).
**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggregation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggregation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml).

---

Expand Down
0 ...ModelServer-ds1.5b-pd-disaggragation.yaml → ...ModelServer-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion docs/kthena/versioned_docs/version-v0.3.0/user-guide/router-routing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,7 +294,7 @@ spec:
4. Prefill runs on prefill instance; decode runs on decode instance, with KV state exchanged between them (configure `kvConnector` for nixl/mooncake when needed)
5. Response returned to client

**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggragation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggragation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml).
**NOTE**: Deploy [ModelServing](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServing-ds1.5b-pd-disaggregation.yaml) with PD roles first, then apply [ModelServer](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelServer-ds1.5b-pd-disaggregation.yaml) and [ModelRoute](https://github.com/volcano-sh/kthena/blob/main/examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml).

---

Expand Down
12 changes: 0 additions & 12 deletions examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml
View file
Open in desktop

This file was deleted.

11 changes: 11 additions & 0 deletions examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
apiVersion: networking.serving.volcano.sh/v1alpha1
kind: ModelRoute
metadata:
name: deepseek-r1-1-5b-pd-disaggregation
namespace: default
spec:
modelName: "deepseek-r1-1-5b-pd-disaggregation"
rules:
- name: "default"
targetModels:
- modelServerName: "deepseek-r1-1-5b-pd-disaggregation"
2 changes: 1 addition & 1 deletion ...ModelServer-ds1.5b-pd-disaggragation.yaml → ...ModelServer-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: networking.serving.volcano.sh/v1alpha1
kind: ModelServer
metadata:
name: deepseek-r1-1-5b-pd-disaggragation
name: deepseek-r1-1-5b-pd-disaggregation
namespace: default
spec:
workloadSelector:
Expand Down
0 ...odelServing-ds1.5b-pd-disaggragation.yaml → ...odelServing-ds1.5b-pd-disaggregation.yaml
View file
Open in desktop
File renamed without changes.
6 changes: 3 additions & 3 deletions test/e2e/router/shared.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,7 +396,7 @@ func TestModelRoutePrefillDecodeDisaggregationShared(t *testing.T, testCtx *rout

// Deploy ModelServing
t.Log("Deploying ModelServing for PD disaggregation...")
modelServing := utils.LoadYAMLFromFile[workloadv1alpha1.ModelServing]("examples/kthena-router/ModelServing-ds1.5b-pd-disaggragation.yaml")
modelServing := utils.LoadYAMLFromFile[workloadv1alpha1.ModelServing]("examples/kthena-router/ModelServing-ds1.5b-pd-disaggregation.yaml")
modelServing.Namespace = testNamespace
createdModelServing, err := testCtx.KthenaClient.WorkloadV1alpha1().ModelServings(testNamespace).Create(ctx, modelServing, metav1.CreateOptions{})
require.NoError(t, err, "Failed to create ModelServing")
Expand All @@ -417,7 +417,7 @@ func TestModelRoutePrefillDecodeDisaggregationShared(t *testing.T, testCtx *rout

// Deploy ModelServer
t.Log("Deploying ModelServer for PD disaggregation...")
modelServer := utils.LoadYAMLFromFile[networkingv1alpha1.ModelServer]("examples/kthena-router/ModelServer-ds1.5b-pd-disaggragation.yaml")
modelServer := utils.LoadYAMLFromFile[networkingv1alpha1.ModelServer]("examples/kthena-router/ModelServer-ds1.5b-pd-disaggregation.yaml")
modelServer.Namespace = testNamespace
createdModelServer, err := testCtx.KthenaClient.NetworkingV1alpha1().ModelServers(testNamespace).Create(ctx, modelServer, metav1.CreateOptions{})
require.NoError(t, err, "Failed to create ModelServer")
Expand All @@ -435,7 +435,7 @@ func TestModelRoutePrefillDecodeDisaggregationShared(t *testing.T, testCtx *rout

// Deploy ModelRoute
t.Log("Deploying ModelRoute for PD disaggregation...")
modelRoute := utils.LoadYAMLFromFile[networkingv1alpha1.ModelRoute]("examples/kthena-router/ModelRoute-ds1.5b-pd-disaggragation.yaml")
modelRoute := utils.LoadYAMLFromFile[networkingv1alpha1.ModelRoute]("examples/kthena-router/ModelRoute-ds1.5b-pd-disaggregation.yaml")
modelRoute.Namespace = testNamespace

// Configure ParentRefs if using Gateway API
Expand Down
Loading