Showing 1–4 of 4 · #inference

Oct 28MODELSQuantization without tears: what you lose at 8, 4 and 3 bits6 min ↗Oct 26TESTSHow to run an 8B LLM on a laptop: hardware, quantization and tools6 min ↗Oct 11PAPERSSpeculative decoding: faster answers without changing them6 min ↗Sep 14PAPERSMixture of experts, without the hype6 min ↗