冯梦轲(翼宏)
Employers on the program
- 2026阿里云1 talk
Events1
Conferences1
Talks1
Years active2026
Upcoming appearances
Who’s booked ahead? →Event dates shown; only events starting today or later count. 1 upcoming event.
-
AICon 全球人工智能开发与应用大会 | 北京 – · Beijing, China
- 从真实 Agent 负载到超节点推理：M890 优化与 ASpeed 集群协同 speaker Program source ↗
No upcoming appearances are currently recorded.
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference)
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Dec 18, 2026 | AICon 全球人工智能开发与应用大会 | 北京 | AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference) | speaker | 从真实 Agent 负载到超节点推理：M890 优化与 ASpeed 集群协同 as 阿里云 问题背景： Agent 应用将大模型推理带入多轮交互、工具调用与上下文持续增长的场景。请求之间的依赖、工具等待和跨轮缓存复用，共同改变了服务的性能瓶颈与资源需求。如何在模型响应时延约束下，提高每张加速卡可交付的服务能力，成为推理系统优化的核心问题 方案与方法论： 本分享以 Abench、M890P加速卡 与…Show less问题背景： Agent 应用将大模型推理带入多轮交互、工具调用与上下文持续增长的场景。请求之间的依赖、工具等待和跨轮缓存复用，共同改变了服务的性能瓶颈与资源需求。如何在模型响应时延约束下，提高每张加速卡可交付的服务能力，成为推理系统优化的核心问题 方案与方法论： 本分享以 Abench、M890P加速卡 与 ASpeed 为主线，介绍贯穿评测、执行和调度的优化方法：通过 Abench 回放真实 Agent 轨迹，保留会话轮次、上下文增长与工具等待，以服务等级目标（SLO）评估容量；在 PPU1.5 上结合低精度、MoE 算子和推测解码优化执行路径；在超节… |
Frequent co-speakers
No one else spoke at two or more of the same events.
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.