公司
别名：togetherai
云服务提供商，专注于为大型语言模型提供高效的推理平台。
已跟踪 9 条高相关材料
最近变化
2026-06-02 · MiniMax M3 supports 1M-token context and native multimodality, making it suitable for complex real-world tasks.
为什么值得关注
Together AI 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without Regrets
Together AI Blog · 8.7 分
Together AI has optimized the deployment of MiniMax M3, a model with 1M-token context and multimodal support, achieving 81–125% throughput...
Engineering voice agents: Latency, quality, and scale — Rishabh Bhargava, Together AI
AI Engineer · 8.5 分
构建高质量、低延迟、可扩展的语音代理已成为工程核心挑战，需解决实时响应（<500ms）、复杂指令处理与工具调用等关键问题，Together AI 提供基础设施支持。
How Together AI built the world’s fastest speech-to-text stack
Together AI Blog · 8.5 分
Together AI optimized their speech-to-text stack, achieving faster transcription speeds by using profile-aware TensorRT, optimizing the dec...
已收录 9 条与 Together AI 相关的内容，按评分排序。
Together AI optimized the deployment of MiniMax M3, achieving 81–125% throughput improvements through architectural and engineering innovations.
入选理由：MiniMax M3 supports 1M-token context and native multimodality, making it suitable for complex real-world tasks.
Building high-quality, low-latency, scalable voice agents is now an engineering challenge requiring real-time response (<500ms), complex instruction handling, and tool calling — supported by Together AI’s infrastructure.
入选理由：语音代理必须在500毫秒内响应，否则用户会挂断电话，实时性是核心指标。
Together AI optimized their speech-to-text stack, achieving faster transcription speeds by using profile-aware TensorRT, optimizing the decoder loop, and improving CPU paths. They serve the two lowest-latency models, with the fastest model transcribing 20 hours of speech in under 10 seconds.
入选理由：Together AI built the world's fastest speech-to-text stack.
Together Inference Engine delivers 31% more TPS than next fastest OSS engine on same hardware, maintains 2× better TTFT at saturation. Performance gains come from full-stack optimization.
入选理由：ThunderMLA、自定义内核重写和端到端优化使Together引擎比其他OSS引擎多31%的TPS
Together AI and Pearl Research Labs have partnered to reduce AI inference costs through technologies like FlashAttention-4 and ATLAS.
入选理由：FlashAttention-4 提升推理速度达 1.3 倍。
Violin is an open-source video translation tool developed by Together AI, using multimodal models to achieve high-quality video content localization.
入选理由：Violin 支持多语言视频翻译，提升跨语言内容可访问性。
Together AI has launched a new tool called Voice Finder, which helps developers quickly find the right voice for their app from over 600 voices.
入选理由：Voice Finder 提供超过 600 种声音选项。
Together AI launches DeepSeek-V4 Pro model with high-performance inference and multiple computing options.
入选理由：DeepSeek-V4 Pro 在 NVIDIA Blackwell 上实现 1.3 倍速度提升。
文章介绍了Together AI的多项技术进展，包括FlashAttention-4、ATLAS加速器和Batch Inference API更新，显著提升了大规模推理效率。
入选理由：FlashAttention-4比cuDNN快1.3倍
