Files
nvfp4-megamoe-kernel/dsv4/ops/quantize.py
biondizzle 9fec7d609e Fix gsa_buffer shape mismatch for MoE (M>1 rows)
compute_amax_gsa returns a scalar, but quantize_from_buffer expects (M,).
Broadcast the scalar gsa to (M,) — all rows use the same gsa (global max).
2026-06-01 21:33:59 +00:00

14 KiB