Skip to content
View original post on X: vLLMOfficial· Same story72/100AI score72/100

vLLM adds day-0 support for Meta's open-weight Muse Spark Open model

AISummary

vLLM says it supports Meta's open-weight Muse Spark Open from day one, verified on NVIDIA and AMD GPUs and TPUs. The model has 816B parameters with 42B active per token and a 1M-token context, with native image, video, audio, and document understanding. vLLM also lists BF16, NVFP4, and MXFP4 precision support and DSpark speculative decoding on CUDA and ROCm.

Post on XView on X
vLLMVerified on X
@vllm_project

🎉 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

This story is featured in top picks: “vLLM adds day 0 support for Meta's Muse Spark Open, a 816B open-weight MoE model”

Source: vLLM · x.comPublished · added here

Topics

Meta / LlamaAI agentsMultimodal AIOpen-source ecosystemDeployment & engineeringProduct updates