@@ -12631,12 +12631,12 @@ components:
1263112631 "target": 1.01} to scale based on queue backlog. Omit or set to null to
1263212632 disable autoscaling'
1263312633 oneOf :
12634- - $ref : ' #/components/schemas/HTTPAutoscalingConfig'
12635- - $ref : ' #/components/schemas/QueueAutoscalingConfig'
12636- - $ref : ' #/components/schemas/CustomMetricAutoscalingConfig'
12634+ - $ref : " #/components/schemas/HTTPAutoscalingConfig"
12635+ - $ref : " #/components/schemas/QueueAutoscalingConfig"
12636+ - $ref : " #/components/schemas/CustomMetricAutoscalingConfig"
1263712637 command :
12638- description : Command overrides the container's ENTRYPOINT. Provide as an array
12639- (e.g., ["/bin/sh", "-c"])
12638+ description : Command overrides the container's ENTRYPOINT. Provide as an
12639+ array (e.g., ["/bin/sh", "-c"])
1264012640 items :
1264112641 type : string
1264212642 type : array
@@ -12650,9 +12650,8 @@ components:
1265012650 deployment
1265112651 type : string
1265212652 environment_variables :
12653- description : EnvironmentVariables is a list of environment variables to set in
12654- the container. Each must have a name and either a value or
12655- value_from_secret
12653+ description : EnvironmentVariables is a list of environment variables to
12654+ set in the container. Each must have a name and either a value or value_from_secret
1265612655 items :
1265712656 $ref : " #/components/schemas/EnvironmentVariable"
1265812657 type : array
@@ -12663,52 +12662,52 @@ components:
1266312662 gpu_type :
1266412663 description : GPUType specifies the GPU hardware to use (e.g., "h100-80gb").
1266512664 enum :
12666- - h100-80gb
12667- - a100-80gb
12665+ - h100-80gb
1266812666 type : string
1266912667 health_check_path :
12670- description : HealthCheckPath is the HTTP path for health checks (e.g.,
12671- " /health" ). If set, the platform will check this endpoint to
12672- determine container health
12668+ description : HealthCheckPath is the HTTP path for health checks (e.g., "/health").
12669+ If set, the platform will check this endpoint to determine container health
1267312670 type : string
1267412671 image :
1267512672 description : Image is the container image to deploy from registry.together.ai.
1267612673 type : string
1267712674 max_replicas :
12678- description : MaxReplicas is the maximum number of container instances that can
12679- be scaled up to. If not set, will be set to MinReplicas
12675+ description : MaxReplicas is the maximum number of container instances that
12676+ can be scaled up to. If not set, will be set to MinReplicas
1268012677 type : integer
1268112678 memory :
12682- description : Memory is the amount of RAM to allocate per container instance in
12683- GiB (e.g., 0.5 = 512MiB)
12684- minimum : 0.1
12679+ description : Memory is the amount of RAM to allocate per container instance
12680+ in GiB (e.g., 0.5 = 512MiB)
12681+ maximum : 1000
1268512682 type : number
1268612683 min_replicas :
12687- description : MinReplicas is the minimum number of container instances to run.
12688- Defaults to 1 if not specified
12684+ description : MinReplicas is the minimum number of container instances to
12685+ run. Defaults to 1 if not specified
1268912686 type : integer
1269012687 name :
1269112688 description : Name is the unique identifier for your deployment. Must contain
12692- only alphanumeric characters, underscores, or hyphens (1-100
12693- characters)
12689+ only alphanumeric characters, underscores, or hyphens (1-100 characters)
1269412690 maxLength : 100
1269512691 minLength : 1
1269612692 type : string
1269712693 port :
12698- description : Port is the container port your application listens on (e.g., 8080
12699- for web servers). Required if your application serves traffic
12694+ description : Port is the container port your application listens on (e.g.,
12695+ 8080 for web servers). Required if your application serves traffic
12696+ maximum : 65535
12697+ minimum : 1
1270012698 type : integer
1270112699 storage :
12702- description : Storage is the amount of ephemeral disk storage to allocate per
12703- container instance (e.g., 10 = 10GiB)
12700+ description : Storage is the amount of ephemeral disk storage to allocate
12701+ per container instance (e.g., 10 = 10GiB)
12702+ maximum : 400
1270412703 type : integer
1270512704 termination_grace_period_seconds :
12706- description : TerminationGracePeriodSeconds is the time in seconds to wait for
12707- graceful shutdown before forcefully terminating the replica
12705+ description : TerminationGracePeriodSeconds is the time in seconds to wait
12706+ for graceful shutdown before forcefully terminating the replica
1270812707 type : integer
1270912708 volumes :
12710- description : Volumes is a list of volume mounts to attach to the container. Each
12711- mount must reference an existing volume by name
12709+ description : Volumes is a list of volume mounts to attach to the container.
12710+ Each mount must reference an existing volume by name
1271212711 items :
1271312712 $ref : " #/components/schemas/VolumeMount"
1271412713 type : array
@@ -12806,6 +12805,7 @@ components:
1280612805 created_at :
1280712806 description : CreatedAt is the ISO8601 timestamp when this deployment was created
1280812807 type : string
12808+ format : date-time
1280912809 description :
1281012810 description : Description provides a human-readable explanation of the
1281112811 deployment's purpose or content
@@ -12890,6 +12890,7 @@ components:
1289012890 description : UpdatedAt is the ISO8601 timestamp when this deployment was last
1289112891 updated
1289212892 type : string
12893+ format : date-time
1289312894 volumes :
1289412895 description : Volumes is a list of volume mounts for this deployment
1289512896 items :
@@ -13105,15 +13106,15 @@ components:
1310513106 type : string
1310613107 type : array
1310713108 autoscaling :
13108- description : Autoscaling configuration for the deployment. Omit or set to
13109- null to disable autoscaling
13109+ description : Autoscaling configuration for the deployment. Set to {} to
13110+ disable autoscaling
1311013111 oneOf :
13111- - $ref : ' #/components/schemas/HTTPAutoscalingConfig'
13112- - $ref : ' #/components/schemas/QueueAutoscalingConfig'
13113- - $ref : ' #/components/schemas/CustomMetricAutoscalingConfig'
13112+ - $ref : " #/components/schemas/HTTPAutoscalingConfig"
13113+ - $ref : " #/components/schemas/QueueAutoscalingConfig"
13114+ - $ref : " #/components/schemas/CustomMetricAutoscalingConfig"
1311413115 command :
13115- description : Command overrides the container's ENTRYPOINT. Provide as an array
13116- (e.g., ["/bin/sh", "-c"])
13116+ description : Command overrides the container's ENTRYPOINT. Provide as an
13117+ array (e.g., ["/bin/sh", "-c"])
1311713118 items :
1311813119 type : string
1311913120 type : array
@@ -13127,8 +13128,8 @@ components:
1312713128 deployment
1312813129 type : string
1312913130 environment_variables :
13130- description : EnvironmentVariables is a list of environment variables to set in
13131- the container. This will replace all existing environment variables
13131+ description : EnvironmentVariables is a list of environment variables to
13132+ set in the container. This will replace all existing environment variables
1313213133 items :
1313313134 $ref : " #/components/schemas/EnvironmentVariable"
1313413135 type : array
@@ -13138,50 +13139,51 @@ components:
1313813139 gpu_type :
1313913140 description : GPUType specifies the GPU hardware to use (e.g., "h100-80gb")
1314013141 enum :
13141- - h100-80gb
13142- - " a100-80gb"
13142+ - h100-80gb
1314313143 type : string
1314413144 health_check_path :
13145- description : HealthCheckPath is the HTTP path for health checks (e.g.,
13146- " /health " ). Set to empty string to disable health checks
13145+ description : HealthCheckPath is the HTTP path for health checks (e.g., "/health").
13146+ Set to empty string to disable health checks
1314713147 type : string
1314813148 image :
1314913149 description : Image is the container image to deploy from registry.together.ai.
1315013150 type : string
1315113151 max_replicas :
13152- description : MaxReplicas is the maximum number of replicas that can be scaled up
13153- to.
13152+ description : MaxReplicas is the maximum number of replicas that can be scaled
13153+ up to.
1315413154 type : integer
1315513155 memory :
13156- description : Memory is the amount of RAM to allocate per container instance in
13157- GiB (e.g., 0.5 = 512MiB)
13158- minimum : 0.1
13156+ description : Memory is the amount of RAM to allocate per container instance
13157+ in GiB (e.g., 0.5 = 512MiB)
13158+ maximum : 1000
1315913159 type : number
1316013160 min_replicas :
1316113161 description : MinReplicas is the minimum number of replicas to run
1316213162 type : integer
1316313163 name :
13164- description : Name is the new unique identifier for your deployment. Must contain
13165- only alphanumeric characters, underscores, or hyphens (1-100
13166- characters)
13164+ description : Name is the new unique identifier for your deployment. Must
13165+ contain only alphanumeric characters, underscores, or hyphens (1-100 characters)
1316713166 maxLength : 100
1316813167 minLength : 1
1316913168 type : string
1317013169 port :
13171- description : Port is the container port your application listens on (e.g., 8080
13172- for web servers)
13170+ description : Port is the container port your application listens on (e.g.,
13171+ 8080 for web servers)
13172+ maximum : 65535
13173+ minimum : 1
1317313174 type : integer
1317413175 storage :
13175- description : Storage is the amount of ephemeral disk storage to allocate per
13176- container instance (e.g., 10 = 10GiB)
13176+ description : Storage is the amount of ephemeral disk storage to allocate
13177+ per container instance (e.g., 10 = 10GiB)
13178+ maximum : 400
1317713179 type : integer
1317813180 termination_grace_period_seconds :
13179- description : TerminationGracePeriodSeconds is the time in seconds to wait for
13180- graceful shutdown before forcefully terminating the replica
13181+ description : TerminationGracePeriodSeconds is the time in seconds to wait
13182+ for graceful shutdown before forcefully terminating the replica
1318113183 type : integer
1318213184 volumes :
13183- description : Volumes is a list of volume mounts to attach to the container. This
13184- will replace all existing volumes
13185+ description : Volumes is a list of volume mounts to attach to the container.
13186+ This will replace all existing volumes
1318513187 items :
1318613188 $ref : " #/components/schemas/VolumeMount"
1318713189 type : array
0 commit comments