当FP4的魔法与Blackwell的强大算力相遇，会碰撞出怎样的火花？ 答案是：推理性能暴涨25倍，成本狂降20倍！ 随着DeepSeek-R1本地化部署的爆火，英伟达也亲自下场，开源了首个基于Blackwell架构的优化方案——DeepSeek-R1-FP4。 在新模型的加持下，B200实现了高达21,088 token ...

Nvidia is banding together with a list of tech partners on a game-changing piece of software that’s set to double the performance of its flagship H100 Tensor Core GPUs. The open source TensorRT-LLM ...