[–] g023 3mo ago ↗ A self-contained CUDA inference engine for LiquidAI/LFM2.5-8B-A1B (hybrid conv + GQA-attention MoE, 8.5B params, 1B active) targeting a single RTX 3060 (12 GB) using flash-decoding. MIT license.
1 comment
[ 3.9 ms ] story [ 14.1 ms ] thread