Event ·Multi-source

Qwen3.8-Flash-Next 与 SGLang 部署

Qwen3.8-Flash-Next 与 SGLang 部署，包含 125B 主模型和 51B N-gram 嵌入，GDN + QSA 混合注意力机制，Gated Residual 结构，Muon 训练。SGLang 为 Qwen4 新架构提供支持。

Current read

Alibaba_Qwen 发布 Qwen3.8-Flash-Next，与 SGLang 合作，模型容量大，嵌入量大，支持长任务，值得期待。

10 sources58° AI heatLast updated 2026/8/26 13:48:52

Evidence

10 sources

Primary source阿里通义 Qwen

2026/8/26 13:48:52View source

Related source 1marktechpost

2026/8/26 15:20:00View source

Related source 2NVIDIA AI

2026/8/26 17:17:05View source

Related source 3orange.ai

2026/8/25 13:27:25View source

Related source 4IT之家

2026/8/25 14:51:37View source

Related source 5lmarena.ai

2026/8/26 15:24:04View source

Related source 6SuperTechFans

2026/8/27 00:44:28View source

Related source 7Paul Couvert

2026/8/26 13:01:43View source

Related source 8shao__meng

2026/8/26 13:11:20View source

Related source 9Decoder

2026/8/26 14:40:09View 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