Wang Xiyuan
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Mengqing Caoonce
- Yikun Jiangonce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| VLLM KV Cache Management: From Cache Reuse To Agent Scenario Optimization | KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 | 2026-09-07 |
As LLM Agents proliferate, the conflict between surging KV Cache and limited VRAM in multi-turn dialogues and tool-chaining has become a key bottleneck. This… | ||
| Bring the Power of ONNX to Spark as it Never Happened Before | Open Source Summit Europe 2022: Open AI + Data Forum | 2022-09-13 |
Adds an ONNX Runtime execution provider for Huawei Ascend so ONNX models run directly on Ascend hardware via CANN/ATC/TBE instead of model translation, with CI… | ||
| nothing matches | ||