trunk/8224fee74a25d6b29b220560fe89bfe94d031d97: flex_gemm: accept 1-D captured tensors (#196183)
- PyTorch 近 90 天出现 1320 次
- PyTorch 近 90 天第 1305 次发版
- 上一次:同一天稍早 · trunk/67d293ec29ed79d56d5ec34bc7117e45c93d0516: [ROCm] Skip conv_transpose1d complex32 reference test on MI200 (#198025)
发生了什么
A closure that captures a 1-D tensor, the natural nn.Parameter shape for a norm weight [N] or a router bias [E] , was rejected with the capture-profile error even when the body wrote w[None, :] , because the profile was checked on the captured tensor rather than on how the body broadcasts it. Running FlexGEMM over DeepSeek-V3's router hit this immediately, and the only workaround was hoisting w2 = w[None, :] outside…
摘要按规则整理自下方来源原文