Ken Zhang
Employers on the program
- 2026华为1 talk
Events1
Conferences1
Talks1
Years active2026
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 |
|---|---|---|---|---|---|
| Jun 26, 2026 | AICon 全球人工智能开发与应用大会 | 上海 | AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference) | speaker | Omni Cache：以内存为中心的KV管理与推理加速 as 华为 本次演讲将聚焦于 Omni Cache 的 DRAM-Centric KV 管理架构设计。将从一个核心问题出发：如何在长上下文大模型推理中，突破 HBM 容量瓶颈，实现数量级的容量扩展与并发提升？ 传统的 PagedAttention 架构将 KV cache 静态预分配在 HBM 中，导致 KV…Show less本次演讲将聚焦于 Omni Cache 的 DRAM-Centric KV 管理架构设计。将从一个核心问题出发：如何在长上下文大模型推理中，突破 HBM 容量瓶颈，实现数量级的容量扩展与并发提升？ 传统的 PagedAttention 架构将 KV cache 静态预分配在 HBM 中，导致 KV 存储与激活张量竞争有限的显存资源。这种 HBM-Centric 设计在模型参数和上下文长度增长时面临三重困境：容量受限、系统隔离、算法复杂。现有 offload 方案保留 HBM block pool 作为权威存储，未能触及核心矛盾。 Omni Cache 引… |
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.