3 repositorios
Awesome GitHub RepositoriesAutomatic ML Workload Batching
Automatic batching of GPU and ML workloads like text embeddings to achieve higher throughput without manual configuration.
Distinct from Automatic Batch Size Optimization: Distinct from Automatic Batch Size Optimization: focuses on batching entire workloads rather than just optimizing batch size for a single model.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Automatic ML Workload Batching. Refine with filters or upvote what's useful.
Awesome Automatic ML Workload Batching GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- cocoindex-io/cocoindex
cocoindex-io/cocoindex
6,117Ver en GitHubCocoindex is an incremental data processing engine that builds and maintains live indexes for AI agents, with a core focus on codebase indexing and knowledge graph extraction. The engine uses a function-graph execution model where user-defined Python functions are composed into a directed acyclic graph, and it processes data incrementally so only changed source records or code paths are re-computed, avoiding full recomputation at any scale. It supports automatic schema inference from transformation pipeline type annotations and provides full data lineage tracing, tagging every output record wi
Automatically batches GPU and ML workloads like text embeddings for higher throughput.
Rustagentic-data-frameworkaiai-agents - reactwg/react-18
reactwg/react-18
5,195Ver en GitHubEste proyecto es un grupo de trabajo de software colaborativo y una pista de lanzamiento centrada en el desarrollo técnico y el despliegue de la actualización de la librería React 18. Sirve como un esfuerzo de coordinación comunitaria y foro de discusión para gestionar los hitos y conjuntos de funciones de esta versión del framework frontend. El grupo de trabajo facilita la coordinación de lanzamientos de código abierto y la planificación de versiones de software a través de un grupo distribuido de colaboradores. Se centra en recopilar comentarios técnicos de la comunidad y gestionar discusiones públicas para refinar el código y la documentación de la librería antes de un lanzamiento formal. El alcance del desarrollo cubre el renderizado concurrente de la interfaz de usuario, la gestión del estado del frontend y el refinamiento de la lógica interna de reconciliación y renderizado.
Groups multiple state updates into a single render pass to improve performance and reduce repaints.
- llm-d/llm-d
llm-d/llm-d
2,514Ver en GitHubllm-d is a distributed serving framework designed for large language model inference. It functions as an inference orchestrator and gateway, providing a control plane for deploying model replicas and managing hardware accelerators. The system includes a batch inference scheduler and a cache manager to coordinate request flow and memory utilization. The project is distinguished by a disaggregated serving architecture that separates prefill and decode execution phases across specialized workers to maximize throughput. It employs a hardware-agnostic control plane and tiered cache offloading, mov
Provides a disaggregated prefill and decode topology specifically designed to maximize throughput for batch-intensive LLM workloads.
Shell
