Primary sourceAnyscale
View sourceEvent ·Multi-source
Anyscale 与 Lila Sciences 将 GLM-5.3-Flash 上下文扩展至 1M tokens 用于基因组训练
基因组序列无法塞进 16k 上下文窗口，Anyscale 的 SkyRL 团队与 Lila Sciences 合作把 GLM-5.3-Flash 的单序列输入扩展到 1M tokens。整个后训练在 64 块 B200 GPU 上完成，用于 AI for Science 场景。训练采用的是完全开源的技术栈。
Current read
基因组一条就是百万 token，他们把 GLM-5.3-Flash 的上下文拉到 1M，用 64 块 B200 训完，全程开源栈能抄作业。
4 sources52° AI heatLast updated 2026/11/5 17:00:10
Evidence
4 sourcesRelated source 1Gorden Sun
View sourceRelated source 2Artificial Analysis
View sourceRelated source 3Thomas Wolf
View sourceConflict 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.