English(EN) day-0 in @vllm_project and it comes with:

MiniMax AI发布开源M3模型，支持100万上下文

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-12 21:16

MiniMax AI发布了其新的开源模型MiniMax M3，该模型拥有100万token的上下文窗口和先进的功能。该模型采用了名为MSA的新型稀疏注意力架构，其中包括专用的预填充和解码内核。它支持NVIDIA Hopper和Blackwell架构上的BF16和MXFP8格式，通过前缀缓存和分块预填充实现了长上下文的高效服务。 AI

影响此次发布突破了开源模型的界限，可能加速长上下文处理和稀疏注意力架构的研究与开发。

排序理由 Frontier-lab模型发布，附带系统卡。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 X — MiniMax AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; Frontier-lab模型发布，附带系统卡。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, 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: 94 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

X — MiniMax AI TIER_1 English(EN) · MiniMax_AI · 2026-06-12 21:16

@vllm_project 的第 0 天，它带来了：

day-0 in @vllm_project and it comes with: dedicated MSA prefill/decode kernels, 1M-context serving with prefix caching + chunked prefill, BF16 + MXFP8 on both Hopper and Blackwell 🚀 this is what open-weight done properly looks like. thanks @vllm_project, @NVIDIAAI, @AIatAMD,

本文如何被排名

报道来源 [1]

@vllm_project 的第 0 天，它带来了：

相关实体

相关话题