Skip to content

Commit 28f3999

Browse files
committed
fix go mod
1 parent e8d45f0 commit 28f3999

File tree

3 files changed

+58
-46
lines changed

3 files changed

+58
-46
lines changed

go.mod

+13-13
Original file line numberDiff line numberDiff line change
@@ -10,26 +10,26 @@ require (
1010
github.com/google/go-cmp v0.6.0
1111
github.com/jhump/protoreflect v1.17.0
1212
github.com/onsi/ginkgo/v2 v2.22.0
13-
github.com/onsi/gomega v1.36.0
13+
github.com/onsi/gomega v1.36.1
1414
github.com/prometheus/client_model v0.6.1
1515
github.com/prometheus/common v0.61.0
1616
github.com/stretchr/testify v1.10.0
1717
go.uber.org/multierr v1.11.0
18-
google.golang.org/grpc v1.68.0
19-
google.golang.org/protobuf v1.35.2
20-
k8s.io/api v0.31.3
21-
k8s.io/apimachinery v0.31.3
22-
k8s.io/client-go v0.31.3
23-
k8s.io/code-generator v0.31.3
24-
k8s.io/component-base v0.31.3
18+
google.golang.org/grpc v1.69.0
19+
google.golang.org/protobuf v1.36.0
20+
k8s.io/api v0.31.4
21+
k8s.io/apimachinery v0.31.4
22+
k8s.io/client-go v0.31.4
23+
k8s.io/code-generator v0.31.4
24+
k8s.io/component-base v0.31.4
2525
k8s.io/klog/v2 v2.130.1
2626
sigs.k8s.io/controller-runtime v0.19.3
27-
sigs.k8s.io/structured-merge-diff/v4 v4.4.3
27+
sigs.k8s.io/structured-merge-diff/v4 v4.5.0
2828
)
2929

3030
require (
31-
cel.dev/expr v0.16.1 // indirect
32-
cloud.google.com/go/compute/metadata v0.5.0 // indirect
31+
cel.dev/expr v0.16.2 // indirect
32+
cloud.google.com/go/compute/metadata v0.5.2 // indirect
3333
github.com/BurntSushi/toml v1.1.0 // indirect
3434
github.com/Masterminds/goutils v1.1.1 // indirect
3535
github.com/Masterminds/semver/v3 v3.2.0 // indirect
@@ -93,8 +93,8 @@ require (
9393
golang.org/x/time v0.3.0 // indirect
9494
golang.org/x/tools v0.26.0 // indirect
9595
gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
96-
google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1 // indirect
97-
google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 // indirect
96+
google.golang.org/genproto/googleapis/api v0.0.0-20241015192408-796eee8c2d53 // indirect
97+
google.golang.org/genproto/googleapis/rpc v0.0.0-20241015192408-796eee8c2d53 // indirect
9898
gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
9999
gopkg.in/inf.v0 v0.9.1 // indirect
100100
gopkg.in/yaml.v2 v2.4.0 // indirect

go.sum

+38-26
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
1-
cel.dev/expr v0.16.1 h1:NR0+oFYzR1CqLFhTAqg3ql59G9VfN8fKq1TCHJ6gq1g=
2-
cel.dev/expr v0.16.1/go.mod h1:AsGA5zb3WruAEQeQng1RZdGEXmBj0jvMWh6l5SnNuC8=
3-
cloud.google.com/go/compute/metadata v0.5.0 h1:Zr0eK8JbFv6+Wi4ilXAR8FJ3wyNdpxHKJNPos6LTZOY=
4-
cloud.google.com/go/compute/metadata v0.5.0/go.mod h1:aHnloV2TPI38yx4s9+wAZhHykWvVCfu7hQbF+9CWoiY=
1+
cel.dev/expr v0.16.2 h1:RwRhoH17VhAu9U5CMvMhH1PDVgf0tuz9FT+24AfMLfU=
2+
cel.dev/expr v0.16.2/go.mod h1:gXngZQMkWJoSbE8mOzehJlXQyubn/Vg0vR9/F3W7iw8=
3+
cloud.google.com/go/compute/metadata v0.5.2 h1:UxK4uu/Tn+I3p2dYWTfiX4wva7aYlKixAHn3fyqngqo=
4+
cloud.google.com/go/compute/metadata v0.5.2/go.mod h1:C66sj2AluDcIqakBq/M8lw8/ybHgOZqin2obFxa/E5k=
55
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
66
github.com/BurntSushi/toml v1.1.0 h1:ksErzDEI1khOiGPgpwuI7x2ebx/uXQNw7xJpn9Eq1+I=
77
github.com/BurntSushi/toml v1.1.0/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
@@ -48,6 +48,8 @@ github.com/fxamacker/cbor/v2 v2.7.0 h1:iM5WgngdRBanHcxugY4JySA0nk1wZorNOpTgCMedv
4848
github.com/fxamacker/cbor/v2 v2.7.0/go.mod h1:pxXPTn3joSm21Gbwsv0w9OSA2y1HFR9qXEeXQVeNoDQ=
4949
github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
5050
github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
51+
github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
52+
github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
5153
github.com/go-logr/zapr v1.3.0 h1:XGdV8XW8zdwFiwOA2Dryh1gj2KRQyOOoNmBy4EplIcQ=
5254
github.com/go-logr/zapr v1.3.0/go.mod h1:YKepepNBd1u/oyhd/yQmtjVXmm9uML4IXUgMOwR8/Gg=
5355
github.com/go-openapi/jsonpointer v0.19.6 h1:eCs3fxoIi3Wh6vtgmLTOjdhSpiqphQ+DaPn38N2ZdrE=
@@ -119,8 +121,8 @@ github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq
119121
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
120122
github.com/onsi/ginkgo/v2 v2.22.0 h1:Yed107/8DjTr0lKCNt7Dn8yQ6ybuDRQoMGrNFKzMfHg=
121123
github.com/onsi/ginkgo/v2 v2.22.0/go.mod h1:7Du3c42kxCUegi0IImZ1wUQzMBVecgIHjR1C+NkhLQo=
122-
github.com/onsi/gomega v1.36.0 h1:Pb12RlruUtj4XUuPUqeEWc6j5DkVVVA49Uf6YLfC95Y=
123-
github.com/onsi/gomega v1.36.0/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
124+
github.com/onsi/gomega v1.36.1 h1:bJDPBO7ibjxcbHMgSCoo4Yj18UWbKDlLwX1x9sybDcw=
125+
github.com/onsi/gomega v1.36.1/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
124126
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
125127
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
126128
github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
@@ -161,6 +163,16 @@ github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcY
161163
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
162164
github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
163165
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
166+
go.opentelemetry.io/otel v1.31.0 h1:NsJcKPIW0D0H3NgzPDHmo0WW6SptzPdqg/L1zsIm2hY=
167+
go.opentelemetry.io/otel v1.31.0/go.mod h1:O0C14Yl9FgkjqcCZAsE053C13OaddMYr/hz6clDkEJE=
168+
go.opentelemetry.io/otel/metric v1.31.0 h1:FSErL0ATQAmYHUIzSezZibnyVlft1ybhy4ozRPcF2fE=
169+
go.opentelemetry.io/otel/metric v1.31.0/go.mod h1:C3dEloVbLuYoX41KpmAhOqNriGbA+qqH6PQ5E5mUfnY=
170+
go.opentelemetry.io/otel/sdk v1.31.0 h1:xLY3abVHYZ5HSfOg3l2E5LUj2Cwva5Y7yGxnSW9H5Gk=
171+
go.opentelemetry.io/otel/sdk v1.31.0/go.mod h1:TfRbMdhvxIIr/B2N2LQW2S5v9m3gOQ/08KsbbO5BPT0=
172+
go.opentelemetry.io/otel/sdk/metric v1.31.0 h1:i9hxxLJF/9kkvfHppyLL55aW7iIJz4JjxTeYusH7zMc=
173+
go.opentelemetry.io/otel/sdk/metric v1.31.0/go.mod h1:CRInTMVvNhUKgSAMbKyTMxqOBC0zgyxzW55lZzX43Y8=
174+
go.opentelemetry.io/otel/trace v1.31.0 h1:ffjsj1aRouKewfr85U2aGagJ46+MvodynlQ1HYdmJys=
175+
go.opentelemetry.io/otel/trace v1.31.0/go.mod h1:TXZkRk7SM2ZQLtR6eoAWQFIHPvzQ06FJAsO1tJg480A=
164176
go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
165177
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
166178
go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
@@ -234,14 +246,14 @@ golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8T
234246
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
235247
gomodules.xyz/jsonpatch/v2 v2.4.0 h1:Ci3iUJyx9UeRx7CeFN8ARgGbkESwJK+KB9lLcWxY/Zw=
236248
gomodules.xyz/jsonpatch/v2 v2.4.0/go.mod h1:AH3dM2RI6uoBZxn3LVrfvJ3E0/9dG4cSrbuBJT4moAY=
237-
google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1 h1:hjSy6tcFQZ171igDaN5QHOw2n6vx40juYbC/x67CEhc=
238-
google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:qpvKtACPCQhAdu3PyQgV4l3LMXZEtft7y8QcarRsp9I=
239-
google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 h1:pPJltXNxVzT4pK9yD8vR9X75DaWYYmLGMsEvBfFQZzQ=
240-
google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
241-
google.golang.org/grpc v1.68.0 h1:aHQeeJbo8zAkAa3pRzrVjZlbz6uSfeOXlJNQM0RAbz0=
242-
google.golang.org/grpc v1.68.0/go.mod h1:fmSPC5AsjSBCK54MyHRx48kpOti1/jRfOlwEWywNjWA=
243-
google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
244-
google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
249+
google.golang.org/genproto/googleapis/api v0.0.0-20241015192408-796eee8c2d53 h1:fVoAXEKA4+yufmbdVYv+SE73+cPZbbbe8paLsHfkK+U=
250+
google.golang.org/genproto/googleapis/api v0.0.0-20241015192408-796eee8c2d53/go.mod h1:riSXTwQ4+nqmPGtobMFyW5FqVAmIs0St6VPp4Ug7CE4=
251+
google.golang.org/genproto/googleapis/rpc v0.0.0-20241015192408-796eee8c2d53 h1:X58yt85/IXCx0Y3ZwN6sEIKZzQtDEYaBWrDvErdXrRE=
252+
google.golang.org/genproto/googleapis/rpc v0.0.0-20241015192408-796eee8c2d53/go.mod h1:GX3210XPVPUjJbTUbvwI8f2IpZDMZuPJWDzDuebbviI=
253+
google.golang.org/grpc v1.69.0 h1:quSiOM1GJPmPH5XtU+BCoVXcDVJJAzNcoyfC2cCjGkI=
254+
google.golang.org/grpc v1.69.0/go.mod h1:vyjdE6jLBI76dgpDojsFGNaHlxdjXN9ghpnd2o7JGZ4=
255+
google.golang.org/protobuf v1.36.0 h1:mjIs9gYtt56AzC4ZaffQuh88TZurBGhIJMBZGSxNerQ=
256+
google.golang.org/protobuf v1.36.0/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
245257
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
246258
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
247259
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
@@ -256,18 +268,18 @@ gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
256268
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
257269
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
258270
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
259-
k8s.io/api v0.31.3 h1:umzm5o8lFbdN/hIXbrK9oRpOproJO62CV1zqxXrLgk8=
260-
k8s.io/api v0.31.3/go.mod h1:UJrkIp9pnMOI9K2nlL6vwpxRzzEX5sWgn8kGQe92kCE=
271+
k8s.io/api v0.31.4 h1:I2QNzitPVsPeLQvexMEsj945QumYraqv9m74isPDKhM=
272+
k8s.io/api v0.31.4/go.mod h1:d+7vgXLvmcdT1BCo79VEgJxHHryww3V5np2OYTr6jdw=
261273
k8s.io/apiextensions-apiserver v0.31.0 h1:fZgCVhGwsclj3qCw1buVXCV6khjRzKC5eCFt24kyLSk=
262274
k8s.io/apiextensions-apiserver v0.31.0/go.mod h1:b9aMDEYaEe5sdK+1T0KU78ApR/5ZVp4i56VacZYEHxk=
263-
k8s.io/apimachinery v0.31.3 h1:6l0WhcYgasZ/wk9ktLq5vLaoXJJr5ts6lkaQzgeYPq4=
264-
k8s.io/apimachinery v0.31.3/go.mod h1:rsPdaZJfTfLsNJSQzNHQvYoTmxhoOEofxtOsF3rtsMo=
265-
k8s.io/client-go v0.31.3 h1:CAlZuM+PH2cm+86LOBemaJI/lQ5linJ6UFxKX/SoG+4=
266-
k8s.io/client-go v0.31.3/go.mod h1:2CgjPUTpv3fE5dNygAr2NcM8nhHzXvxB8KL5gYc3kJs=
267-
k8s.io/code-generator v0.31.3 h1:Pj0fYOBms+ZrsulLi4DMsCEx1jG8fWKRLy44onHsLBI=
268-
k8s.io/code-generator v0.31.3/go.mod h1:/umCIlT84g1+Yu5ZXtP1KGSRTnGiIzzX5AzUAxsNlts=
269-
k8s.io/component-base v0.31.3 h1:DMCXXVx546Rfvhj+3cOm2EUxhS+EyztH423j+8sOwhQ=
270-
k8s.io/component-base v0.31.3/go.mod h1:xME6BHfUOafRgT0rGVBGl7TuSg8Z9/deT7qq6w7qjIU=
275+
k8s.io/apimachinery v0.31.4 h1:8xjE2C4CzhYVm9DGf60yohpNUh5AEBnPxCryPBECmlM=
276+
k8s.io/apimachinery v0.31.4/go.mod h1:rsPdaZJfTfLsNJSQzNHQvYoTmxhoOEofxtOsF3rtsMo=
277+
k8s.io/client-go v0.31.4 h1:t4QEXt4jgHIkKKlx06+W3+1JOwAFU/2OPiOo7H92eRQ=
278+
k8s.io/client-go v0.31.4/go.mod h1:kvuMro4sFYIa8sulL5Gi5GFqUPvfH2O/dXuKstbaaeg=
279+
k8s.io/code-generator v0.31.4 h1:Vu+8fKz+239rKiVDHFVHgjQ162cg5iUQPtTyQbwXeQw=
280+
k8s.io/code-generator v0.31.4/go.mod h1:yMDt13Kn7m4MMZ4LxB1KBzdZjEyxzdT4b4qXq+lnI90=
281+
k8s.io/component-base v0.31.4 h1:wCquJh4ul9O8nNBSB8N/o8+gbfu3BVQkVw9jAUY/Qtw=
282+
k8s.io/component-base v0.31.4/go.mod h1:G4dgtf5BccwiDT9DdejK0qM6zTK0jwDGEKnCmb9+u/s=
271283
k8s.io/gengo/v2 v2.0.0-20240228010128-51d4e06bde70 h1:NGrVE502P0s0/1hudf8zjgwki1X/TByhmAoILTarmzo=
272284
k8s.io/gengo/v2 v2.0.0-20240228010128-51d4e06bde70/go.mod h1:VH3AT8AaQOqiGjMF9p0/IM1Dj+82ZwjfxUP1IxaHE+8=
273285
k8s.io/klog/v2 v2.130.1 h1:n9Xl7H1Xvksem4KFG4PYbdQCQxqc/tTUyrgXaOhHSzk=
@@ -280,7 +292,7 @@ sigs.k8s.io/controller-runtime v0.19.3 h1:XO2GvC9OPftRst6xWCpTgBZO04S2cbp0Qqkj8b
280292
sigs.k8s.io/controller-runtime v0.19.3/go.mod h1:j4j87DqtsThvwTv5/Tc5NFRyyF/RF0ip4+62tbTSIUM=
281293
sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd h1:EDPBXCAspyGV4jQlpZSudPeMmr1bNJefnuqLsRAsHZo=
282294
sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd/go.mod h1:B8JuhiUyNFVKdsE8h686QcCxMaH6HrOAZj4vswFpcB0=
283-
sigs.k8s.io/structured-merge-diff/v4 v4.4.3 h1:sCP7Vv3xx/CWIuTPVN38lUPx0uw0lcLfzaiDa8Ja01A=
284-
sigs.k8s.io/structured-merge-diff/v4 v4.4.3/go.mod h1:N8f93tFZh9U6vpxwRArLiikrE5/2tiu1w1AGfACIGE4=
295+
sigs.k8s.io/structured-merge-diff/v4 v4.5.0 h1:nbCitCK2hfnhyiKo6uf2HxUPTCodY6Qaf85SbDIaMBk=
296+
sigs.k8s.io/structured-merge-diff/v4 v4.5.0/go.mod h1:N8f93tFZh9U6vpxwRArLiikrE5/2tiu1w1AGfACIGE4=
285297
sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
286298
sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=

pkg/ext-proc/scheduling/filter.go

+7-7
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,11 @@
11
package scheduling
22

33
import (
4-
"fmt"
4+
"errors"
55
"math"
66

7-
klog "k8s.io/klog/v2"
8-
97
"inference.networking.x-k8s.io/llm-instance-gateway/pkg/ext-proc/backend"
8+
klog "k8s.io/klog/v2"
109
)
1110

1211
type Filter interface {
@@ -86,7 +85,7 @@ func toFilterFunc(pp podPredicate) filterFunc {
8685
}
8786
}
8887
if len(filtered) == 0 {
89-
return nil, fmt.Errorf("no pods left")
88+
return nil, errors.New("no pods left")
9089
}
9190
return filtered, nil
9291
}
@@ -157,9 +156,10 @@ func leastKVCacheFilterFunc(req *LLMRequest, pods []*backend.PodMetrics) ([]*bac
157156
type podPredicate func(req *LLMRequest, pod *backend.PodMetrics) bool
158157

159158
// We consider serving an adapter low cost it the adapter is active in the model server, or the
160-
// model server has room to load the adapter. The lowLoRACostPredicate ensures weak affinity by spreading the
161-
// load of a LoRA adapter across multiple pods, avoiding "pinning" all requests to a single pod.
162-
// This gave good performance in our initial benchmarking results in the scenario where # of lora slots > # of lora adapters.
159+
// model server has room to load the adapter. The lowLoRACostPredicate ensures weak affinity by
160+
// spreading the load of a LoRA adapter across multiple pods, avoiding "pinning" all requests to
161+
// a single pod. This gave good performance in our initial benchmarking results in the scenario
162+
// where # of lora slots > # of lora adapters.
163163
func lowLoRACostPredicate(req *LLMRequest, pod *backend.PodMetrics) bool {
164164
_, ok := pod.ActiveModels[req.ResolvedTargetModel]
165165
return ok || len(pod.ActiveModels) < pod.MaxActiveModels

0 commit comments

Comments
 (0)