LLM Inference & Deployment Frameworks

6 repos

This cluster covers infrastructure and frameworks for running large language models in production, with emphasis on conversational AI endpoints and text generation. The repositories focus on model optimization, inference serving, and compatibility with standard transformer architectures, using formats like safetensors for efficient model loading. While anchored by prominent DeepSeek model releases (R1, V3, V4 variants) and MiniMax implementations, the cluster's dominant signal is practical tooling for deploying and serving LLMs at scale.

Related clusters