[PyTorch] Propagate skip_fp8_weight_update in GroupedLinear during FP8 CUDA graph capture#3065

Open

LeSingh1 wants to merge 2 commits into

NVIDIA:mainfrom

LeSingh1:fix-grouped-linear-skip-fp8-weight-update-3051

Commits on Jun 1, 2026

[PyTorch] Propagate skip_fp8_weight_update in GroupedLinear during FP8 CUDA graph capture
LeSingh1
committed
[PyTorch] Add CUDA graph FP8 weight-caching test for GroupedLinear
LeSingh1
committed