biondizzle ea8acf9852 Share padded_x_sf and output buffers across layers to save ~300 MB ...

Per-layer padded_xsf (2.4 MB) + output_buf (4.2 MB) × 60 layers = ~400 MB.
Sharing reduces to ~3.6 MB total. Layers run sequentially during both
capture and replay.

2026-05-17 16:05:53 +00:00

..

patches

Fix shape mismatch: shared padded buffers, revert max_num_tokens cap

2026-05-17 15:47:10 +00:00

nvfp4_cutedsl.py

Share padded_x_sf and output buffers across layers to save ~300 MB

2026-05-17 16:05:53 +00:00