PulseAugur
中
实时 09:33:22
English(EN) Prime Intellect has launched Prime Inference, a serverless serving platform for frontier open models running on NVIDIA Blackwell GPUs. The platform processes ne

Prime Intellect 推出 Prime Inference 开源模型推理平台

作者 PulseAugur 编辑部 · [2 个来源] ·

Prime Intellect 推出了 Prime Inference，一个专为前沿开源 AI 模型设计的新型推理平台。该平台利用 NVIDIA Blackwell GPU，提供用于应对可变需求的无服务器端点和用于持续工作负载的预留容量。Prime Inference 旨在通过结合 NVIDIA Dynamo、vLLM、Mooncake 和 FlashInfer 等技术来优化性能，并支持与 OpenAI 兼容的 API。 AI

影响 该平台可以为开发人员和企业简化开源 AI 模型的部署和扩展。

排序理由 这是一个面向开源模型的推理平台的产品发布，而不是来自主要实验室的前沿模型发布。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Prime Intellect 推出 Prime Inference 开源模型推理平台

本文如何被排名

Signal score
8 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一个面向开源模型的推理平台的产品发布，而不是来自主要实验室的前沿模型发布。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [2]

  1. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

    Prime Intellect推出Prime Inference：面向前沿开源模型的无服务器和预留服务

    <p>Prime Intellect has launched Prime Inference, an OpenAI-compatible platform for serving frontier open models on NVIDIA Blackwell. Its GLM-5.3 deployment uses Dynamo, vLLM and NVFP4 KV compression to serve 66 sessions per prefill group at 101 tok/s per user.</p> <p>The post <a …

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Prime Intellect推出Prime Inference，一个在NVIDIA Blackwell GPU上运行前沿开源模型的无服务器推理平台。该平台处理...

    Prime Intellect has launched Prime Inference, a serverless serving platform for frontier open models running on NVIDIA Blackwell GPUs. The platform processes nearly a trillion tokens daily for AI agents and supports OpenAI-compatible APIs. https://www. marktechpost.com/2026/10/02…

相关实体

相关话题