SGLang adds Day-0 support for Muse Spark Open, an 816B open-weight multimodal model

SGLang 为 816B 开源多模态 MoE 模型 Muse Spark Open 提供 Day-0 支持

SGLang shipped Day-0 support for Muse Spark Open, an 816B open-weight multimodal model. The release adds sequence parallelism, NVFP4 MegaMoE, multimodal processing optimizations and DFlash V2 speculative decoding. Across seven concurrency levels, combining sequence parallelism with MegaMoE for long-prompt prefill cut p90 time to first token by 28.3% to 41.9%.

Why it matters: It pairs sequence parallelism with MegaMoE for long-prompt prefill and reports p90 time-to-first-token cuts of 28.3% to 41.9% across seven concurrency levels.