biondizzle 2a2a42c6d6 Add attention-internal diagnostics: MLA output, FP8 quant output

2026-05-18 14:45:43 +00:00

..

patches

Add attention-internal diagnostics: MLA output, FP8 quant output

2026-05-18 14:45:43 +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