1 repository
Awesome GitHub RepositoriesWorkload-Based Model Selectors
Routes inference requests to the model best suited for the task, optimizing for latency, cost, or accuracy.
Distinct from Request Routing by Model ID: Distinct from Request Routing by Model ID: selects models based on workload characteristics, not just a static model ID.
Explore 1 awesome GitHub repository matching data & databases · Workload-Based Model Selectors. Refine with filters or upvote what's useful.
Awesome Workload-Based Model Selectors GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- vllm-project/semantic-router
vllm-project/semantic-router
3,205Vezi pe GitHubRoutes each inference request to the model best suited for its task, optimizing for latency, cost, or accuracy.
Goai-gatewaybert-classificationfine-tuning
