biondizzle c5af1aba6b Fix OOB: size padded buffers for num_experts*max_chunks*128 ...

padded_max_slots was computed from max_tokens*top_k (3072) but
total_padded_slots in run() is num_experts*max_chunks*128 (6144).
The buffer was too small, causing index out of bounds.

2026-05-17 14:59:45 +00:00

..

patches

Fix OOM: cap buffer pre-allocation at cudagraph max capture size

2026-05-17 14:14:13 +00:00

nvfp4_cutedsl.py

Fix OOB: size padded buffers for num_experts*max_chunks*128

2026-05-17 14:59:45 +00:00