1
Kog is going deeper to squeeze more inference out of GPUs
Kog专攻现有数据中心GPU的极致推理提速，演示单请求极速解码，还拿下200条销售线索，值得关注。
The idea that GPUs are poorly suited for agentic workflows may be a misconception, according to French startup Kog.
2
AirLLM Runs a 70B Model on a 4GB GPU. It's True, and That's Not the Interesting Part
70B大模型跑进4GB显存，不靠量化保住全精度，原理比结果更惊艳
AirLLM's README opens with a line that sounds like it can't be true: AirLLM dramatically reduces inference memory usage, letting 70B large language mo…