LLM inference

AI DeepSeek v4 Flash is so cheap it should embarrass every Western AI lab with a pricing page

4 min 1.2K views

AI Llama.cpp's auto fit feature is quietly reshaping what local AI inference can do on consumer hardware

4 min 1.6K views

AI sllm Wants to Split Your GPU Costs With a Cohort Sharing Model

5 min 235 views