GLM-5.3-Flash Architecture Notes
Architecture note on GLM-5.3-Flash, formerly Ox Alpha, covering its KDA and MLA/DSA hybrid attention, sparse MoE backbone, and four-stream mHC residual path.
点赞
收藏
点踩
分享评论
?
参与讨论
Architecture note on GLM-5.3-Flash, formerly Ox Alpha, covering its KDA and MLA/DSA hybrid attention, sparse MoE backbone, and four-stream mHC residual path.