Meta open-weights Muse Spark Open: 816B-A42B MoE with 1M context, day-0 on vLLM
vllm_project · x · 2026-10-16
vLLM announced day-0 support for Meta's open-weight Muse Spark Open, verified on NVIDIA and AMD GPUs plus TPUs. The 816B-parameter (42B active) sparse MoE targets long-horizon agentic coding with 1M-token context for large codebases, native image/video/audio/document understanding, BF16/NVFP4/MXFP4 support, and DSpark speculative decoding on CUDA and ROCm. Billed as the most capable US open-weight model.
Related event: Meta Open-Sources Muse Spark Open: 816B-Parameter MoE with 1M Context(54 posts)→
More from Infra
- llama.cpp v0.7.0 adds GPU LRU cache for host-memory MoE experts, up to 2.2x faster decode — EAccelerate_42 · 2026-10-16
- NVIDIA ships Nemotron 3.5 Bolt: 74B-A9B model in 24GB of memory — NVIDIAAI · 2026-10-16
- Creative Strategies launches CS Forecast Stack: 19 linked models covering AI's full economic chain — BenBajarin · 2026-10-16
- Copper to optical: optical backplanes seen as necessary as racks move to optics — BenBajarin · 2026-10-16
- Polymarket prices 28% odds a US state enacts data center moratorium by year-end — Polymarket · 2026-10-16
- Pennsylvania residents reject $10,000-per-household offer for massive Amazon data center — Polymarket · 2026-10-16