vLLM BlogSame event7878vLLM supported Mistral Large 4 on the first day
vLLM announced support for Mistral Large 4 on the release day, which is a 1 trillion parameter, 49B token-activated MoE native multimodal model, using MLA with DSA sparse indexer, and built-in DSpark speculative decoding draft model.
Same story — showing the featured version《Mistral Large 4 (Le Chonk) released on Hugging Face》