Event ·Official first-hand

NVIDIA 演示 DGX Spark 上三层 MoE 推理优化，Ling-3.0-flash 吞吐提升 42.5%

NVIDIA 在单台 DGX Spark 上叠加三项优化加速 MoE 推理。测试模型为 Ant Group inclusionAI 的 124B 参数 Ling-3.0-flash。GSM8K 解码吞吐量提升 42.5%，准确率无可检测变化。

Current read

NVIDIA 在 DGX Spark 上叠三层优化跑 Ling-3.0-flash，GSM8K 解码吞吐直接提了 42.5%，准确率没掉，做本地推理的可以抄作业。

5 sources43° AI heatLast updated 2026/11/3 20:28:22

Evidence

5 sources

Primary sourcemarktechpost

2026/11/3 20:28:22View source

Related source 1arXiv cs.AI

2026/11/3 03:04:04View source

Related source 2LlamaIndex

2026/11/3 16:49:05View source

Related source 3IT之家

2026/11/3 23:21:17View source

Related source 4vLLM

2026/11/4 00:00:21View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story