biondizzle ff74b33d2c Fix cudagraph: static loop for per-expert scale swizzle ...

The while loop had variable trip count (GPU scalar in condition),
requiring CPU-GPU sync. Replaced with fixed max_chunks_per_expert
iterations. Unused chunks are zero buffers (harmless for GEMM).

2026-05-17 13:56:52 +00:00

..

patches

Fix warmup: pass local expert IDs (not global), remove incorrect _warmup_done guard

2026-05-17 11:38:19 +00:00

nvfp4_cutedsl.py

Fix cudagraph: static loop for per-expert scale swizzle

2026-05-17 13:56:52 +00:00