Skip to content

build(llm-router): allow always-disagg deciders in llm-d-router observer #762

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
thxCode merged 1 commit into from
Oct 15, 2026
Merged

build(llm-router): allow always-disagg deciders in llm-d-router observer #762

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
5 changes: 3 additions & 2 deletions pack/llm-router/patches/llm-d/0001-observer-endpoints-and-dispatch.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -768,7 +768,7 @@ new file mode 100644
index 00000000..b6db1667
--- /dev/null
+++ b/pkg/epp/observer/endpoints.go
@@ -0,0 +1,261 @@
@@ -0,0 +1,262 @@
+// Copyright 2026 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
Expand Down Expand Up @@ -838,6 +838,7 @@ index 00000000..b6db1667
+ "core-metrics-extractor", "approx-prefix-cache-producer",
+ "precise-prefix-cache-producer", "token-producer", "endpoint-notification-source",
+ "prefix-based-pd-decider", "disagg-profile-handler", "single-profile-handler",
+ "always-disagg-pd-decider", "always-disagg-multimodal-decider",
+ "openai-parser", "anthropic-parser", "vllmhttp-parser", "passthrough-parser",
+ "fcfs-ordering-policy", "global-strict-fairness-policy",
+ "static-usage-limit-policy-type", "utilization-detector":
Expand Down Expand Up @@ -1187,7 +1188,7 @@ index 00000000..45d030eb
+ want bool
+ }{
+ {name: "missing", want: false}, {name: "operator default", types: []string{"single-profile-handler", "label-selector-filter", "queue-scorer", "kv-cache-utilization-scorer", "max-score-picker", "prefix-cache-scorer", "metrics-data-source", "core-metrics-extractor", "approx-prefix-cache-producer"}, want: true},
+ {name: "operator disaggregation", types: []string{"disagg-profile-handler", "prefix-based-pd-decider", "precise-prefix-cache-producer", "token-producer", "endpoint-notification-source"}, want: true},
+ {name: "operator disaggregation", types: []string{"disagg-profile-handler", "prefix-based-pd-decider", "always-disagg-pd-decider", "always-disagg-multimodal-decider", "precise-prefix-cache-producer", "token-producer", "endpoint-notification-source"}, want: true},
+ {name: "unknown plugin", types: []string{"single-profile-handler", "retains-private-candidates"}, want: false},
+ } {
+ t.Run(tt.name, func(t *testing.T) {
Expand Down
Loading