Qwen3.8-Flash-Next在NVIDIA GB300 NVL72上支持代理编码
原标题:Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
AI 摘要
阿里巴巴发布了Qwen3.8-Flash-Next模型权重,作为Qwen4架构的预览,供开发者实验和评估。该模型是一个多模态MoE模型,主模型125B参数,附加51B N-gram嵌入,每token激活6B参数,原生上下文窗口262,144 token,可通过YaRN扩展到1M。NVIDIA提供了Day 0功能支持,包括SGLang、vLLM和TensorRT LLM,并在GB300 NVL72上验证推理性能,同时提供NeMo AutoModel和NeMo RL的微调与强化学习配方。该模型专为高容量、上下文密集型应用设计,如代理编码、文档处理和工具驱动工作流,其混合架构结合了Gated DeltaNet和Qwen Sparse Attention,以解决长上下文下的注意力计算和KV缓存瓶颈。在GB300 NVL72上,模型实现了每GPU每秒超过16K tokens的吞吐量,每用户每秒超过200 tokens,支持高吞吐低延迟的代理编码应用。
正文节选
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s a multimodal mixture-of-experts (MoE) model with a 125B-parameter main model supplemented by an additional 51B N-gram embeddings, with 6B parameters activated per token. It has a native 262,144-token context window, extensible to 1M tokens with YaRN. NVIDIA provides best-effort Day 0 functional support through SGLang, vLLM, and NVIDIA Tens