II.
SkillArea overview
Reference · liveskill-area:model-serving-operations
Model Serving overview
Operating deployed inference endpoints - rollout shape, latency control, scaling, routing, and serving-path reliability for ML systems.
Attributes
displayName
Model Serving
description
Operating deployed inference endpoints - rollout shape, latency control,
scaling, routing, and serving-path reliability for ML systems.
domains
expertiseLevels
- intermediate
- expert
Outgoing edges
applies_to1
- specialization:ml-inference-serving·SpecializationML Inference Serving
uses_stack_part1
- stack-part:model-serving·StackPartModel Serving / Inference Endpoint
Incoming edges
lib_requires_skill_area4
- lib-agent:ai-agents-conversational--latency-optimizer·LibraryAgentlatency-optimizer
- lib-agent:data-science-ml--deployment-engineer·LibraryAgentdeployment-engineer
- lib-skill:data-science-ml--bentoml-model-packager·LibrarySkillbentoml-model-packager
- lib-skill:data-science-ml--seldon-model-deployer·LibrarySkillseldon-model-deployer
prerequisite_for_learning2
- skill-area:model-serving·SkillAreaModel Serving
- skill-area:machine-learning·SkillAreaMachine Learning
requires_skill_area2
- skill-area:model-serving-deployment·SkillAreaModel Serving and Deployment
- skill-area:inference-performance-testing·SkillAreaInference Performance Testing
tool_used_by3
- tool:litellm·ToolLiteLLM
- tool:openrouter·ToolOpenRouter
- tool:portkey-ai·ToolPortkey AI