SGLang and Miles add day-0 support for Muse Spark Open
An LMSYS blog post says SGLang and Miles have added day-0 support for Muse Spark Open, an open-weight multimodal mixture-of-experts model. Its text backbone has 816B parameters with roughly 42B active parameters per token, accepts text, image, video and audio inputs, supports a 1M-token context window, and ships NVFP4 and BF16 checkpoints. The SGLang integration adds sequence parallelism with NVFP4 MegaMoE for prefill, multimodal preprocessing optimizations and DFlash V2 speculative decoding; the team reports that on 8 NVIDIA B300 GPUs with the NVFP4 checkpoint, an OpenHands multi-turn agentic coding replay reaches 14.8K total tokens/sec per GPU at concurrency 1 and 80.3K at concurrency 128.
For newly released open-weight models, getting fast day-one support in mainstream inference stacks increasingly shapes how quickly developers can actually adopt them.