Serve DeepSeek-V4.1-Flash-1017 from two NVIDIA DGX Sparks through an OpenAI-compatible API, with the full 1M-token window, image input, tool calling, thinking on or off, and DSpark speculative decoding
Breakthrough inference speed for MiniMax H3 Reference-to-Video (Ref2VA / R2VA): Generate a full 5-second, 24 fps video conditioned on reference character images in ~72s (warm) / 95s (first run) on a single consumer NVIDIA GeForce RTX 4090 (24GB)
