Import part 17

ubiops-deployments/deployments/deployment-gpt-oss-chat/versions/deployment_gpt-oss-120b_version_v-gpt-120b-v3.yaml

@@ -0,0 +1,33 @@
+version_name: "v-gpt-120b-v3"
+version_description: ""
+version_labels: 
+  import: "0a5d8365-be73-4ab7-9933-2fb93468a8de"
+  model-names: "openai/gpt-oss-120b"
+  openai-compatible: "true"
+environment: "python3-12"
+instance_type: "16gb_8vcpu_rtxpro"
+static_ip: False
+minimum_instances: 1
+maximum_instances: 1
+maximum_idle_time: 10
+request_retention_mode: "full"
+request_retention_time: 2419200
+maximum_queue_size: 100000
+scaling_strategy: "default"
+instance_processes: 20
+health_check: 
+  path: "/health"
+  port: 8000
+  timeout: 3
+  interval: 5
+  failure_threshold: 3
+ports: []
+version_environment_variables:
+  - name: "VLLM_USE_V1"
+    value: "1"
+  - name: "MODEL_NAME"
+    value: "openai/gpt-oss-120b"
+  - name: "GPU_MEMORY_UTILIZATION"
+    value: "0.90"
+  - name: "MAX_MODEL_LEN"
+    value: "125000"

ubiops-deployments/deployments/deployments-embedder/deployment_bge-m3/deployment_bge-m3.yaml

@@ -0,0 +1,10 @@
+deployment_name: "bge-m3"
+deployment_description: ""
+deployment_labels: {}
+default_version: "v3"
+supports_request_format: True
+input_type: "plain"
+input_fields: []
+output_type: "plain"
+output_fields: []
+deployment_environment_variables: []

ubiops-deployments/deployments/deployments-embedder/deployment_bge-m3/versions/deployment_bge-m3_version_v3.yaml

@@ -0,0 +1,22 @@
+version_name: "v3"
+version_description: ""
+version_labels: {}
+environment: "python3-13"
+instance_type: "8gb_2vcpu_rtxpro_1mig"
+static_ip: False
+minimum_instances: 1
+maximum_instances: 1
+maximum_idle_time: 300
+request_retention_mode: "metadata"
+request_retention_time: 2419200
+maximum_queue_size: 100000
+scaling_strategy: "default"
+instance_processes: 1
+health_check: 
+  path: "/health"
+  port: 8000
+  timeout: 3
+  interval: 5
+  failure_threshold: 3
+ports: []
+version_environment_variables: []

ubiops-deployments/deployments/deployments-proxies/deployment_llm-proxy/deployment_llm-proxy.yaml

@@ -0,0 +1,15 @@
+deployment_name: "llm-proxy"
+deployment_description: ""
+deployment_labels: 
+  type: "llm-proxy"
+  created-by: "ubiops"
+default_version: "v11"
+supports_request_format: True
+input_type: "plain"
+input_fields: []
+output_type: "plain"
+output_fields: []
+deployment_environment_variables: 
+  - name: "UBIOPS_API_TOKEN"
+    value: ""
+    secret: True

ubiops-deployments/deployments/deployments-proxies/deployment_llm-proxy/versions/deployment_llm-proxy_version_v11.yaml

@@ -0,0 +1,16 @@
+version_name: "v11"
+version_description: "Support for gpt oss + gpt oss x2 + gpt oss x3 + gemma. No cooldowns"
+version_labels: {}
+environment: "python3-12"
+instance_type: "4096mb"
+static_ip: False
+minimum_instances: 1
+maximum_instances: 2
+maximum_idle_time: 300
+request_retention_mode: "full"
+request_retention_time: 2419200
+maximum_queue_size: 100000
+scaling_strategy: "default"
+instance_processes: 1
+ports: []
+version_environment_variables: []

ubiops-deployments/deployments/deployments-proxies/deployment_proxy-gpt-oss-batch-3x/deployment_proxy-gpt-oss-batch-3x.yaml

@@ -0,0 +1,11 @@
+deployment_name: "proxy-gpt-oss-batch-3x"
+deployment_description: ""
+deployment_labels: 
+  type: "llm-proxy"
+default_version: "v1"
+supports_request_format: True
+input_type: "plain"
+input_fields: []
+output_type: "plain"
+output_fields: []
+deployment_environment_variables: []

ubiops-deployments/deployments/deployments-proxies/deployment_proxy-gpt-oss-batch-3x/versions/deployment_proxy-gpt-oss-batch-3x_version_v1.yaml

@@ -0,0 +1,24 @@
+version_name: "v1"
+version_description: "Requests 2 GPT Oss\u0027es"
+version_labels: 
+  type: "llm-proxy"
+environment: "python3-12"
+instance_type: "4096mb"
+static_ip: False
+minimum_instances: 1
+maximum_instances: 3
+maximum_idle_time: 300
+request_retention_mode: "full"
+request_retention_time: 2419200
+maximum_queue_size: 100000
+scaling_strategy: "default"
+instance_processes: 18
+ports: []
+version_environment_variables:
+  - name: "UBIOPS_API_TOKEN"
+    value: ""
+    secret: True
+  - name: "UBIOPS_DEPLOYMENT_VERSIONS"
+    value: "[[\"gpt-oss-120b\",\"v-gpt-120b-tool-calling-max-12\"],[\"gpt-oss-120b\",\"v-gpt-120b-tool-calling\"],[\"gpt-oss-120b\",\"v-gpt-120b-v3\"]]"
+  - name: "POLL_INTERVAL"
+    value: "1"

ubiops-deployments/info.yaml

@@ -0,0 +1,3 @@
+format_spec: v8.0
+metadata:
+  export_date: 2026-06-02T07:52:13.765643+00:00