OpenAI Ultrafast推理达300 tok/s
OpenAI announced up to 300 tokens per second with Ultrafast. According to SemiAn…
OpenAI announced up to 300 tokens per second with Ultrafast. According to SemiAnalysis, it’s running on NVIDIA GPUs. That’s particularly interesting given its partnership with Cerebras specifically for ultra-low-latency inference.
OpenAI 宣布 Ultrafast 模型每秒可处理多达 300 个 token。据 SemiAnalysis 报道，其运行在 NVIDIA GPU 上。鉴于 OpenAI 与 Cerebras 专门针对超低延迟推理的合作关系，这一点尤其引人关注。
According to SemiAnalysis, OpenAI is using NVIDIA GPUs at a low batch size, prioritizing speed for individual requests.
据 SemiAnalysis 报道，OpenAI 正在使用 NVIDIA GPU，并以较小的批次大小（batch size）运行，优先保障单个请求的速度。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力