Kimi-Linear-48B

Researchers introduced DAMP (Decay-Aware Mixed-Precision Recurrent-State Quantization), a post-training quantization method for recurrent-state language models, which reduces recurrent-state storage b…

Veso AI open-sourced tenstorrent-wormhole-kimi-linear, kernels and correctness gates that run Kimi-Linear-48B on Tenstorrent Wormhole hardware, taking the model from not starting to serving 16,384 tok…

RunInfra enables running Kimi-Linear-48B, a distilled version of the full 2.78-trillion-parameter Kimi K3 model, on a single consumer GPU such as the RTX 5090 with 32 GB VRAM, achieving 113.83 tokens …