vLLM 首日支持 Meta 开源模型 Muse Spark Open
Meta 放了个 816B 的开源模型 Muse Spark Open，支持 1M 上下文还能看图看视频，vLLM 当天就能跑，写代码的智能体场景可以试试。
Meta Superintelligence Labs 发布开源权重模型 Muse Spark Open，共 816B 参数，每 token 激活 42B。vLLM 在发布首日提供支持，已在 NVIDIA、AMD GPU 及 TPU 上完成验证。该模型支持 1M token 上下文输入，可处理图像、视频、音频和文档，面向长周期智能体编程场景。vLLM 同时提供 BF16、NVFP4、MXFP4 量化格式和 DSpark 投机解码，覆盖 CUDA 与 ROCm 平台。
🎉 Day-0 support for Meta's open-weight Muse Spark Open is live on vLLM, verified on NVIDIA and AMD GPUs as well as on TPUs!
816B parameters, 42B active per token, a 1M-token image, video and audio inputs, built for long-horizon agentic coding.
We’re excited to have worked with Meta Superintelligence Labs to bring Muse Spark Open to vLLM from day one as the most capable US open-weight model.
✨ 1M context for large, complex codebases 👀 Native image, video, audio & document understanding ⚡ BF16, NVFP4 & MXFP4 support 🚀 DSpark speculative decoding on both CUDA and ROCm
1/6
