biondizzle 5c1dda10f6 Add granular attention diagnostics: pre/post attn, embed, dequant stats

2026-05-18 14:24:14 +00:00

..

patches

Add granular attention diagnostics: pre/post attn, embed, dequant stats

2026-05-18 14:24:14 +00:00

nvfp4_cutedsl.py

HOTFIX: remove NaN checks from run() — torch.isnan().any() does CPU-GPU sync, breaks cudagraph

2026-05-17 22:28:32 +00:00