Skip to content

Commit a27100d

Browse files
authored
sync with IGW release 1.0.0-rc (#320)
* sync with IGW release 1.0.0-rc.3 Signed-off-by: Nir Rozenbaum <[email protected]> * kebab-case flags Signed-off-by: Nir Rozenbaum <[email protected]> * fix test rbac Signed-off-by: Nir Rozenbaum <[email protected]> --------- Signed-off-by: Nir Rozenbaum <[email protected]>
1 parent f35a2ef commit a27100d

File tree

16 files changed

+200
-111
lines changed

16 files changed

+200
-111
lines changed

Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ ENV GOOS=${TARGETOS:-linux}
3636
ENV GOARCH=${TARGETARCH}
3737
ARG COMMIT_SHA=unknown
3838
ARG BUILD_REF
39-
RUN go build -a -o bin/epp -ldflags="-extldflags '-L$(pwd)/lib' -X sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics.CommitSHA=${COMMIT_SHA} -X sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics.BuildRef=${BUILD_REF}" cmd/epp/main.go
39+
RUN go build -a -o bin/epp -ldflags="-extldflags '-L$(pwd)/lib' -X sigs.k8s.io/gateway-api-inference-extension/version.CommitSHA=${COMMIT_SHA} -X sigs.k8s.io/gateway-api-inference-extension/version.BuildRef=${BUILD_REF}" cmd/epp/main.go
4040

4141
# Use ubi9 as a minimal base image to package the manager binary
4242
# Refer to https://catalog.redhat.com/software/containers/ubi9/ubi-minimal/615bd9b4075b022acc111bf5 for more details

cmd/epp/main.go

Lines changed: 1 addition & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -34,15 +34,10 @@ import (
3434
)
3535

3636
func main() {
37-
ctx := ctrl.SetupSignalHandler()
38-
39-
// Register GIE plugins
40-
runner.RegisterAllPlugins()
41-
4237
// Register llm-d-inference-scheduler plugins
4338
plugins.RegisterAllPlugins()
4439

45-
if err := runner.NewRunner().Run(ctx); err != nil {
40+
if err := runner.NewRunner().Run(ctrl.SetupSignalHandler()); err != nil {
4641
os.Exit(1)
4742
}
4843
}

deploy/components/crds-gie/kustomization.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,4 +10,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
1010
kind: Kustomization
1111

1212
resources:
13-
- https://github.com/kubernetes-sigs/gateway-api-inference-extension/config/crd?ref=v0.5.1
13+
- https://github.com/kubernetes-sigs/gateway-api-inference-extension/config/crd?ref=v1.0.0-rc.3

deploy/components/inference-gateway/deployments.yaml

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -21,15 +21,17 @@ spec:
2121
image: ghcr.io/llm-d/llm-d-inference-scheduler:latest
2222
imagePullPolicy: IfNotPresent
2323
args:
24-
- -poolName
24+
- --pool-name
2525
- "${POOL_NAME}"
26-
- -v
26+
- "--pool-group"
27+
- "inference.networking.x-k8s.io"
28+
- --v
2729
- "4"
2830
- --zap-encoder
2931
- "json"
30-
- -grpcPort
32+
- --grpc-port
3133
- "9002"
32-
- -grpcHealthPort
34+
- --grpc-health-port
3335
- "9003"
3436
env:
3537
- name: PYTHONHASHSEED

deploy/environments/dev/base-kind-istio/patch-deployments.yaml

Lines changed: 8 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -8,17 +8,19 @@ spec:
88
containers:
99
- name: epp
1010
args:
11-
- -poolName
11+
- --pool-name
1212
- ${POOL_NAME}
13-
- -poolNamespace
13+
- --pool-namespace
1414
- "default"
15-
- -v
15+
- "--pool-group"
16+
- "inference.networking.x-k8s.io"
17+
- --v
1618
- "4"
1719
- --zap-encoder
1820
- "json"
19-
- -grpcPort
21+
- --grpc-port
2022
- "9002"
21-
- -grpcHealthPort
23+
- --grpc-health-port
2224
- "9003"
23-
- --configFile
25+
- --config-file
2426
- "/etc/epp/epp-config.yaml"

deploy/environments/dev/kubernetes-kgateway/patch-deployments.yaml

Lines changed: 8 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -10,19 +10,21 @@ spec:
1010
image: ${EPP_IMAGE}:${EPP_TAG}
1111
imagePullPolicy: Always
1212
args:
13-
- -poolName
13+
- --pool-name
1414
- ${POOL_NAME}
15-
- -poolNamespace
15+
- --pool-namespace
1616
- ${NAMESPACE}
17-
- -v
17+
- "--pool-group"
18+
- "inference.networking.x-k8s.io"
19+
- --v
1820
- "4"
1921
- --zap-encoder
2022
- "json"
21-
- -grpcPort
23+
- --grpc-port
2224
- "9002"
23-
- -grpcHealthPort
25+
- --grpc-health-port
2426
- "9003"
25-
- --configFile
27+
- --config-file
2628
- "/etc/epp/epp-config.yaml"
2729
env:
2830
- name: HF_TOKEN

go.mod

Lines changed: 16 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@ toolchain go1.24.2
77
require (
88
github.com/go-logr/logr v1.4.3
99
github.com/google/go-cmp v0.7.0
10+
github.com/google/uuid v1.6.0
1011
github.com/jellydator/ttlcache/v3 v3.4.0
1112
github.com/llm-d/llm-d-kv-cache-manager v0.2.1
1213
github.com/onsi/ginkgo/v2 v2.25.2
@@ -20,7 +21,7 @@ require (
2021
k8s.io/client-go v0.34.0
2122
sigs.k8s.io/controller-runtime v0.22.0
2223
sigs.k8s.io/gateway-api v1.3.0
23-
sigs.k8s.io/gateway-api-inference-extension v0.5.1
24+
sigs.k8s.io/gateway-api-inference-extension v1.0.0-rc.3
2425
)
2526

2627
require (
@@ -29,11 +30,12 @@ require (
2930
github.com/antlr4-go/antlr/v4 v4.13.0 // indirect
3031
github.com/beorn7/perks v1.0.1 // indirect
3132
github.com/blang/semver/v4 v4.0.0 // indirect
32-
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
33+
github.com/cenkalti/backoff/v5 v5.0.2 // indirect
3334
github.com/cespare/xxhash/v2 v2.3.0 // indirect
3435
github.com/cncf/xds/go v0.0.0-20250501225837-2ac532fd4443 // indirect
3536
github.com/daulet/tokenizers v1.22.1 // indirect
3637
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
38+
github.com/dennwc/varint v1.0.0 // indirect
3739
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
3840
github.com/emicklei/go-restful/v3 v3.12.2 // indirect
3941
github.com/envoyproxy/go-control-plane/envoy v1.32.4 // indirect
@@ -52,9 +54,9 @@ require (
5254
github.com/google/btree v1.1.3 // indirect
5355
github.com/google/cel-go v0.26.0 // indirect
5456
github.com/google/gnostic-models v0.7.0 // indirect
55-
github.com/google/pprof v0.0.0-20250403155104-27863c87afa6 // indirect
56-
github.com/google/uuid v1.6.0 // indirect
57+
github.com/google/pprof v0.0.0-20250607225305-033d6d78b36a // indirect
5758
github.com/gorilla/websocket v1.5.4-0.20250319132907-e064f32e3674 // indirect
59+
github.com/grafana/regexp v0.0.0-20240518133315-a468a5bfb3bc // indirect
5860
github.com/grpc-ecosystem/grpc-gateway/v2 v2.26.3 // indirect
5961
github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
6062
github.com/inconshreveable/mousetrap v1.1.0 // indirect
@@ -70,10 +72,11 @@ require (
7072
github.com/pkg/errors v0.9.1 // indirect
7173
github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 // indirect
7274
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
73-
github.com/prometheus/client_golang v1.22.0 // indirect
75+
github.com/prometheus/client_golang v1.23.0 // indirect
7476
github.com/prometheus/client_model v0.6.2 // indirect
7577
github.com/prometheus/common v0.65.0 // indirect
76-
github.com/prometheus/procfs v0.15.1 // indirect
78+
github.com/prometheus/procfs v0.16.1 // indirect
79+
github.com/prometheus/prometheus v0.305.0 // indirect
7780
github.com/redis/go-redis/v9 v9.11.0 // indirect
7881
github.com/spf13/cobra v1.9.1 // indirect
7982
github.com/spf13/pflag v1.0.6 // indirect
@@ -86,27 +89,28 @@ require (
8689
github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
8790
github.com/x448/float16 v0.8.4 // indirect
8891
go.opentelemetry.io/auto/sdk v1.1.0 // indirect
89-
go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0 // indirect
92+
go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 // indirect
9093
go.opentelemetry.io/otel v1.37.0 // indirect
91-
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.34.0 // indirect
92-
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.34.0 // indirect
94+
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.36.0 // indirect
95+
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.36.0 // indirect
9396
go.opentelemetry.io/otel/metric v1.37.0 // indirect
9497
go.opentelemetry.io/otel/sdk v1.37.0 // indirect
9598
go.opentelemetry.io/otel/trace v1.37.0 // indirect
96-
go.opentelemetry.io/proto/otlp v1.5.0 // indirect
99+
go.opentelemetry.io/proto/otlp v1.6.0 // indirect
100+
go.uber.org/atomic v1.11.0 // indirect
97101
go.uber.org/automaxprocs v1.6.0 // indirect
98102
go.uber.org/multierr v1.11.0 // indirect
99103
go.uber.org/zap v1.27.0 // indirect
100104
go.yaml.in/yaml/v2 v2.4.2 // indirect
101105
go.yaml.in/yaml/v3 v3.0.4 // indirect
102-
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 // indirect
106+
golang.org/x/exp v0.0.0-20250106191152-7588d65b2ba8 // indirect
103107
golang.org/x/net v0.43.0 // indirect
104108
golang.org/x/oauth2 v0.30.0 // indirect
105109
golang.org/x/sync v0.16.0 // indirect
106110
golang.org/x/sys v0.35.0 // indirect
107111
golang.org/x/term v0.34.0 // indirect
108112
golang.org/x/text v0.28.0 // indirect
109-
golang.org/x/time v0.9.0 // indirect
113+
golang.org/x/time v0.12.0 // indirect
110114
golang.org/x/tools v0.36.0 // indirect
111115
gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
112116
google.golang.org/genproto/googleapis/api v0.0.0-20250707201910-8d1bb00bc6a7 // indirect

0 commit comments

Comments
 (0)