Tool
Source-linked workflows that name vLLM. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
US lab Reflection open-sourced Beam (501B MoE / 23B active, 1M context, Apache 2.0) for coding and long-horizon agents, with day-0 vLLM/SGLang/Transformers support, Mirror CLI harness, and 40+ inference partners including OpenRouter and Ollama.
Tencent Hunyuan open-weights Hy-Memory-30B-A3B (~3B active MoE) to replace the general LLM on the write path of Mem0/MemOS/Hy-Memory—trained with on-policy distillation + attributed memory RL; beats Claude Opus 5 / DeepSeek V4.1 Flash on a fixed cross-harness memory-writer matrix; Apache-friendly HF weights + GitHub framework.
IBM Granite Switch 4.1 (Oct 15, HF blog): 8B/30B compose chat + Decision aLoRA + Guardian safety aLoRA + Granite-Speech-5.0-Turbo-CTC ASR in ~base VRAM via Activated LoRAs with shared KV cache—swap chat/decision/speech on one endpoint; vLLM plugin and llama.cpp support; community can mix Granite Libraries adapters.
Oct 15 open weights: multimodal MoE (816B total / 42B active, 1M context) trained for long-horizon coding agents—plan, tool-call, self-correct—with Muse Code demos shipping real iOS changes on-device; HF + API hosts.
inclusionAI/Ant Ling open-sourced Ling-3.1-flash (560B total / ~25B active, 1M context, MIT) for agents, office, search, and SWE—day-0 SGLang/vLLM recipes, tool/reasoning parsers, and strong Terminal-Bench / SWE-bench Pro / SkillsBench numbers; works in Claude Code, Hermes, OpenClaw, and related harnesses.