智能体
blogs.nvidia.com ·
@Dion Harris
NVIDIA GPU 加速 OpenAI GPT-6 Astra Ultrafast，token 生成最高提速 8 倍
NVIDIA 官方博客称，GPT-6 Astra Ultrafast 运行于 NVIDIA Blackwell GPU，现已通过 OpenAI API 向开发者开放，并向符合条件的 ChatGPT Work 和 Codex 用户提供。借助针对 Blackwell 架构的推理优化，Ultrafast 的 token 生成速度最高可达 Astra Standard 模式的 8 倍。NVIDIA 表示，更快的生成可缩短编码 Agent 的编辑-测试-调试周期、减少工具调用之间的响应等待，并提升交互式应用的响应感。OpenAI 推理负责人 Philippe Tillet 与算力 CTO Uday Ruddarraju 在文中表示，双方利用 OpenAI 内部模型优化 NVIDIA GPU 上的推理软件，NVIDIA 平台的可编程性支撑了此次加速。开发者可通过 API 使用该模式，访问方式、定价与实现细节见 Ultrafast 指南。
AI推荐理由 NVIDIA 官方博客披露 GPT-6 Astra Ultrafast 已在 OpenAI API 及符合条件的 ChatGPT Work、Codex 用户中上线，基于 NVIDIA Blackwell GPU，token 生成速度最高为 Astra Standard 模式的 8 倍，并引用 OpenAI 推理负责人与算力 CTO 的具名表态。新信息具体：面向开发者的用途是缩短编码 Agent 的编辑-测试-调试循环、减少工具调用间等待；局限是 8 倍加速为厂商自述、未给出独立基准，且定价与实现细节需另查 Ultrafast 指南。
82
正文
GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users. Accelerated by inference optimizations through OpenAI’s models that tap into the capabilities of the NVIDIA Blackwell architecture, Ultrafast offers up to 8x faster token generation than the Astra Standard mode. For developers, faster generation can shorten coding agents’ edit-test-debug cycles, reduce the time spent generating responses between tool calls and make interactive applications feel more responsive. A faster response matters most when it’s repeated across a workflow: an agent writes code, uses a tool, checks the result and decides what to do next. Ultrafast brings Astra’s capabilities into these time-sensitive loops. NVIDIA AI infrastructure helps OpenAI serve more useful model outputs when developers need it. “NVIDIA’s deep investment in tooling and documentation has enabled us to make our models exceptionally good at programming Blackwell and Rubin GPUs,” said Philippe Tillet, inference lead at OpenAI. “Astra can turn that knowledge into high-performance kernels that make NVIDIA hardware compelling across the full frontier of latency, throughput and cost. With Astra Ultrafast, that means faster model responses as agents write code, use tools and work through complex tasks.” Continually Improving Performance Performance gains don’t stop when a model is deployed. OpenAI is using its own models to help refine the inference software running on NVIDIA GPUs, taking advantage of the platform’s programmability to test and implement improvements. That ongoing work can make model responses faster and deployed infrastructure more productive over time. “Our work with NVIDIA is helping us make AI faster and more useful,” said Uday Ruddarraju, chief technology officer of compute at OpenAI. “We used our internal models to optimize inference on NVIDIA GPUs, and NVIDIA’s programmability helped us deliver the acceleration behind Astra Ultrafast.” A programmable NVIDIA platform allows developers and researchers to reuse infrastructure across training, inference and reinforcement learning as models evolve. That flexibility helps teams repurpose compute resources as demand changes, improving utilization and avoiding overprovision for each workload. Developers can use GPT-6 Astra Ultrafast through the API today. See the Ultrafast guide for access, pricing and implementation details.