Skip to content

Commit 995af3f

Browse files
tchapkfswain
tchap
authored and
kfswain
committed
Rename pkg/ext-proc to pkg/epp (kubernetes-sigs#372)
1 parent 9bc51b3 commit 995af3f

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

51 files changed

+112
-110
lines changed

‎Dockerfile

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ ARG BUILDER_IMAGE=golang:1.23-alpine
44
ARG BASE_IMAGE=gcr.io/distroless/base-debian10
55

66
## Multistage build
7-
FROM ${BUILDER_IMAGE} as builder
7+
FROM ${BUILDER_IMAGE} AS builder
88
ENV CGO_ENABLED=0
99
ENV GOOS=linux
1010
ENV GOARCH=amd64
@@ -19,13 +19,13 @@ COPY cmd ./cmd
1919
COPY pkg ./pkg
2020
COPY internal ./internal
2121
COPY api ./api
22-
WORKDIR /src/cmd/ext-proc
23-
RUN go build -o /ext-proc
22+
WORKDIR /src/cmd/epp
23+
RUN go build -o /epp
2424

2525
## Multistage deploy
2626
FROM ${BASE_IMAGE}
2727

2828
WORKDIR /
29-
COPY --from=builder /ext-proc /ext-proc
29+
COPY --from=builder /epp /epp
3030

31-
ENTRYPOINT ["/ext-proc"]
31+
ENTRYPOINT ["/epp"]

‎cmd/ext-proc/health.go renamed to ‎cmd/epp/health.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -23,8 +23,8 @@ import (
2323
"google.golang.org/grpc/codes"
2424
healthPb "google.golang.org/grpc/health/grpc_health_v1"
2525
"google.golang.org/grpc/status"
26-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
27-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
26+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
27+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2828
)
2929

3030
type healthServer struct {

‎cmd/ext-proc/main.go renamed to ‎cmd/epp/main.go

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -41,12 +41,12 @@ import (
4141
"sigs.k8s.io/controller-runtime/pkg/metrics/filters"
4242
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
4343
"sigs.k8s.io/gateway-api-inference-extension/internal/runnable"
44-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/backend"
45-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/backend/vllm"
46-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
47-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/metrics"
48-
runserver "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/server"
49-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
44+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/backend"
45+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/backend/vllm"
46+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
47+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics"
48+
runserver "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/server"
49+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
5050
)
5151

5252
const (

‎docs/dev.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ const(
3737
)
3838
```
3939

40-
The guidelines are written in the context of a k8s controller. Our [ext-proc](../pkg/ext-proc/) does more things such as handling requests and scraping metrics, therefore we adapt the guidelines as follows:
40+
The guidelines are written in the context of a k8s controller. Our [epp](../pkg/epp/) does more things such as handling requests and scraping metrics, therefore we adapt the guidelines as follows:
4141

4242
1. The server startup process and configuration.
4343

‎docs/proposals/003-endpoint-picker-protocol/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
The Endpoint Picker, or EPP, is a core component of the inference extension. Ultimately it's
44
responsible for picking an endpoint from the `InferencePool`. A reference implementation can be
5-
found [here](../../../pkg/ext-proc/).
5+
found [here](../../../pkg/epp/).
66

77
## Proxy Protocol
88

‎pkg/ext-proc/backend/fake.go renamed to ‎pkg/epp/backend/fake.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -22,8 +22,8 @@ import (
2222
"k8s.io/apimachinery/pkg/types"
2323
"sigs.k8s.io/controller-runtime/pkg/log"
2424
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
25-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
26-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
25+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
26+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2727
)
2828

2929
type FakePodMetricsClient struct {

‎pkg/ext-proc/backend/provider.go renamed to ‎pkg/epp/backend/provider.go

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -25,9 +25,9 @@ import (
2525
"github.com/go-logr/logr"
2626
"go.uber.org/multierr"
2727
"sigs.k8s.io/controller-runtime/pkg/log"
28-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
29-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/metrics"
30-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
28+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
29+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics"
30+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3131
)
3232

3333
const (

‎pkg/ext-proc/backend/provider_test.go renamed to ‎pkg/epp/backend/provider_test.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ import (
2727
"github.com/google/go-cmp/cmp/cmpopts"
2828
"github.com/stretchr/testify/assert"
2929
"k8s.io/apimachinery/pkg/types"
30-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
30+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
3131
)
3232

3333
var (

‎pkg/ext-proc/backend/vllm/metrics.go renamed to ‎pkg/epp/backend/vllm/metrics.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -30,8 +30,8 @@ import (
3030
"github.com/prometheus/common/expfmt"
3131
"go.uber.org/multierr"
3232
"sigs.k8s.io/controller-runtime/pkg/log"
33-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
34-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
33+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
34+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3535
)
3636

3737
const (

‎pkg/ext-proc/backend/vllm/metrics_test.go renamed to ‎pkg/epp/backend/vllm/metrics_test.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -23,8 +23,8 @@ import (
2323
dto "github.com/prometheus/client_model/go"
2424
"github.com/stretchr/testify/assert"
2525
"google.golang.org/protobuf/proto"
26-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
27-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
26+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
27+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2828
)
2929

3030
func TestPromToPodMetrics(t *testing.T) {

‎pkg/ext-proc/controller/inferencemodel_reconciler.go renamed to ‎pkg/epp/controller/inferencemodel_reconciler.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -28,8 +28,8 @@ import (
2828
"sigs.k8s.io/controller-runtime/pkg/client"
2929
"sigs.k8s.io/controller-runtime/pkg/log"
3030
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
31-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
32-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
31+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
32+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3333
)
3434

3535
type InferenceModelReconciler struct {

‎pkg/ext-proc/controller/inferencemodel_reconciler_test.go renamed to ‎pkg/epp/controller/inferencemodel_reconciler_test.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -29,8 +29,8 @@ import (
2929
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
3030
"k8s.io/apimachinery/pkg/types"
3131
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
32-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
33-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
32+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
33+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3434
)
3535

3636
var (

‎pkg/ext-proc/controller/inferencepool_reconciler.go renamed to ‎pkg/epp/controller/inferencepool_reconciler.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -28,8 +28,8 @@ import (
2828
"sigs.k8s.io/controller-runtime/pkg/client"
2929
"sigs.k8s.io/controller-runtime/pkg/log"
3030
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
31-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
32-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
31+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
32+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3333
)
3434

3535
// InferencePoolReconciler utilizes the controller runtime to reconcile Instance Gateway resources

‎pkg/ext-proc/controller/inferencepool_reconciler_test.go renamed to ‎pkg/epp/controller/inferencepool_reconciler_test.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -31,8 +31,8 @@ import (
3131
"sigs.k8s.io/controller-runtime/pkg/client"
3232
"sigs.k8s.io/controller-runtime/pkg/client/fake"
3333
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
34-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
35-
utiltesting "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/testing"
34+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
35+
utiltesting "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/testing"
3636
)
3737

3838
var (

‎pkg/ext-proc/controller/pod_reconciler.go renamed to ‎pkg/epp/controller/pod_reconciler.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -28,8 +28,8 @@ import (
2828
ctrl "sigs.k8s.io/controller-runtime"
2929
"sigs.k8s.io/controller-runtime/pkg/client"
3030
"sigs.k8s.io/controller-runtime/pkg/log"
31-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
32-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
31+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
32+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3333
)
3434

3535
type PodReconciler struct {

‎pkg/ext-proc/controller/pod_reconciler_test.go renamed to ‎pkg/epp/controller/pod_reconciler_test.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ import (
3232
"sigs.k8s.io/controller-runtime/pkg/client"
3333
"sigs.k8s.io/controller-runtime/pkg/client/fake"
3434
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
35-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
35+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
3636
)
3737

3838
var (

‎pkg/ext-proc/datastore/datastore.go renamed to ‎pkg/epp/datastore/datastore.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ import (
2929
"sigs.k8s.io/controller-runtime/pkg/client"
3030
"sigs.k8s.io/controller-runtime/pkg/log"
3131
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
32-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
32+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3333
)
3434

3535
// The datastore is a local cache of relevant data for the given InferencePool (currently all pulled from k8s-api)

‎pkg/ext-proc/datastore/datastore_test.go renamed to ‎pkg/epp/datastore/datastore_test.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ import (
2121

2222
v1 "k8s.io/apimachinery/pkg/apis/meta/v1"
2323
"sigs.k8s.io/gateway-api-inference-extension/api/v1alpha1"
24-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
24+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2525
)
2626

2727
func TestHasSynced(t *testing.T) {

‎pkg/ext-proc/datastore/types.go renamed to ‎pkg/epp/datastore/types.go

File renamed without changes.

‎pkg/ext-proc/handlers/request.go renamed to ‎pkg/epp/handlers/request.go

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ import (
2626
extProcPb "github.com/envoyproxy/go-control-plane/envoy/service/ext_proc/v3"
2727
"google.golang.org/protobuf/types/known/structpb"
2828
"sigs.k8s.io/controller-runtime/pkg/log"
29-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
30-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/scheduling"
31-
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/error"
32-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
29+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
30+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/scheduling"
31+
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/error"
32+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3333
)
3434

3535
// HandleRequestBody handles body of the request to the backend server, such as parsing the "model"

‎pkg/ext-proc/handlers/response.go renamed to ‎pkg/epp/handlers/response.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -24,8 +24,8 @@ import (
2424
configPb "github.com/envoyproxy/go-control-plane/envoy/config/core/v3"
2525
extProcPb "github.com/envoyproxy/go-control-plane/envoy/service/ext_proc/v3"
2626
"sigs.k8s.io/controller-runtime/pkg/log"
27-
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/error"
28-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
27+
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/error"
28+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2929
)
3030

3131
// HandleResponseHeaders processes response headers from the backend model server.

‎pkg/ext-proc/handlers/response_test.go renamed to ‎pkg/epp/handlers/response_test.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ import (
2222

2323
extProcPb "github.com/envoyproxy/go-control-plane/envoy/service/ext_proc/v3"
2424
"github.com/google/go-cmp/cmp"
25-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
25+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2626
)
2727

2828
const (

‎pkg/ext-proc/handlers/server.go renamed to ‎pkg/epp/handlers/server.go

Lines changed: 5 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -27,11 +27,11 @@ import (
2727
"google.golang.org/grpc/codes"
2828
"google.golang.org/grpc/status"
2929
"sigs.k8s.io/controller-runtime/pkg/log"
30-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
31-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/metrics"
32-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/scheduling"
33-
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/error"
34-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
30+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
31+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics"
32+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/scheduling"
33+
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/error"
34+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3535
)
3636

3737
func NewServer(scheduler Scheduler, targetEndpointKey string, datastore datastore.Datastore) *Server {
@@ -185,7 +185,6 @@ func (s *Server) Process(srv extProcPb.ExternalProcessor_ProcessServer) error {
185185
return status.Errorf(codes.Unknown, "failed to send response back to Envoy: %v", err)
186186
}
187187
}
188-
189188
}
190189

191190
// RequestContext stores context information during the life time of an HTTP request.

‎pkg/ext-proc/metrics/README.md renamed to ‎pkg/epp/metrics/README.md

File renamed without changes.

‎pkg/ext-proc/metrics/metrics.go renamed to ‎pkg/epp/metrics/metrics.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ import (
2424
compbasemetrics "k8s.io/component-base/metrics"
2525
"k8s.io/component-base/metrics/legacyregistry"
2626
"sigs.k8s.io/controller-runtime/pkg/log"
27-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
27+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2828
)
2929

3030
const (

‎pkg/ext-proc/metrics/metrics_test.go renamed to ‎pkg/epp/metrics/metrics_test.go

Lines changed: 26 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -24,8 +24,8 @@ import (
2424

2525
"k8s.io/component-base/metrics/legacyregistry"
2626
"k8s.io/component-base/metrics/testutil"
27-
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/error"
28-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
27+
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/error"
28+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2929
)
3030

3131
const (
@@ -119,31 +119,32 @@ func TestRecordRequestErrorCounter(t *testing.T) {
119119
name string
120120
reqs []requests
121121
invalid bool
122-
}{{
123-
name: "multiple requests",
124-
reqs: []requests{
125-
{
126-
modelName: "m10",
127-
targetModelName: "t10",
128-
error: errutil.Internal,
129-
},
130-
{
131-
modelName: "m10",
132-
targetModelName: "t10",
133-
error: errutil.Internal,
134-
},
135-
{
136-
modelName: "m10",
137-
targetModelName: "t11",
138-
error: errutil.ModelServerError,
139-
},
140-
{
141-
modelName: "m20",
142-
targetModelName: "t20",
143-
error: errutil.InferencePoolResourceExhausted,
122+
}{
123+
{
124+
name: "multiple requests",
125+
reqs: []requests{
126+
{
127+
modelName: "m10",
128+
targetModelName: "t10",
129+
error: errutil.Internal,
130+
},
131+
{
132+
modelName: "m10",
133+
targetModelName: "t10",
134+
error: errutil.Internal,
135+
},
136+
{
137+
modelName: "m10",
138+
targetModelName: "t11",
139+
error: errutil.ModelServerError,
140+
},
141+
{
142+
modelName: "m20",
143+
targetModelName: "t20",
144+
error: errutil.InferencePoolResourceExhausted,
145+
},
144146
},
145147
},
146-
},
147148
}
148149
Register()
149150
for _, scenario := range scenarios {

‎pkg/ext-proc/metrics/testdata/input_tokens_metric renamed to ‎pkg/epp/metrics/testdata/input_tokens_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/kv_cache_avg_metrics renamed to ‎pkg/epp/metrics/testdata/kv_cache_avg_metrics

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/output_tokens_metric renamed to ‎pkg/epp/metrics/testdata/output_tokens_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/queue_avg_size_metrics renamed to ‎pkg/epp/metrics/testdata/queue_avg_size_metrics

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/request_duration_seconds_metric renamed to ‎pkg/epp/metrics/testdata/request_duration_seconds_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/request_error_total_metric renamed to ‎pkg/epp/metrics/testdata/request_error_total_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/request_sizes_metric renamed to ‎pkg/epp/metrics/testdata/request_sizes_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/request_total_metric renamed to ‎pkg/epp/metrics/testdata/request_total_metric

File renamed without changes.

‎pkg/ext-proc/metrics/testdata/response_sizes_metric renamed to ‎pkg/epp/metrics/testdata/response_sizes_metric

File renamed without changes.

‎pkg/ext-proc/scheduling/filter.go renamed to ‎pkg/epp/scheduling/filter.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -21,8 +21,8 @@ import (
2121
"math"
2222

2323
"github.com/go-logr/logr"
24-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
25-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
24+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
25+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2626
)
2727

2828
type Filter interface {

‎pkg/ext-proc/scheduling/filter_test.go renamed to ‎pkg/epp/scheduling/filter_test.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -23,8 +23,8 @@ import (
2323
"github.com/go-logr/logr"
2424
"github.com/google/go-cmp/cmp"
2525
"k8s.io/apimachinery/pkg/types"
26-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
27-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
26+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
27+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
2828
)
2929

3030
func TestFilter(t *testing.T) {

‎pkg/ext-proc/scheduling/scheduler.go renamed to ‎pkg/epp/scheduling/scheduler.go

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -24,9 +24,9 @@ import (
2424

2525
"github.com/go-logr/logr"
2626
"sigs.k8s.io/controller-runtime/pkg/log"
27-
"sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/datastore"
28-
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/error"
29-
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/ext-proc/util/logging"
27+
"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
28+
errutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/error"
29+
logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
3030
)
3131

3232
const (
@@ -102,7 +102,8 @@ var (
102102
filter: func(logger logr.Logger, req *LLMRequest, pods []*datastore.PodMetrics) ([]*datastore.PodMetrics, error) {
103103
logger.V(logutil.DEFAULT).Info("Request dropped", "request", req)
104104
return []*datastore.PodMetrics{}, errutil.Error{
105-
Code: errutil.InferencePoolResourceExhausted, Msg: "dropping request due to limited backend resources"}
105+
Code: errutil.InferencePoolResourceExhausted, Msg: "dropping request due to limited backend resources",
106+
}
106107
},
107108
},
108109
}

‎pkg/ext-proc/scheduling/types.go renamed to ‎pkg/epp/scheduling/types.go

File renamed without changes.

0 commit comments

Comments
 (0)