Bijaya Dangol

🚀 vLLM v0.14.0 is here! 660 commits from 251 contributors (86 new! 🎉). Breaking changes included - read before upgrading. Key highlights: ⚡ Async scheduling enabled by default 🔌 gRPC server entrypoint 🧠 --max-model-len auto 📦 PyTorch 2.9.1 required More: 👇

New Model Support: 🦎 Grok-2 with tiktoken tokenizer 👁️ LFM2-VL vision-language model ⚡ MiMo-V2-Flash 🎙️ GLM-ASR audio 🧩 K-EXAONE-236B-A23B MoE LoRA now supports multimodal tower/connector for LLaVA, BLIP2, PaliGemma, Pixtral, and more 🔥

The majority of the ruff ruff is people who look at the current point and people who look at the current slope.