biondizzle 583ad6cfe6 P0 complete: Kill .item() in grouped_linear, reduce hot-path syncs ...

- grouped_linear.py: Replace .item() gsa + Python quantize with
  quantize_nvfp4_gpu_fused (zero CPU syncs). Flatten all groups
  into (G*T, D), single fused kernel launch, GPU-only gsa copy.
- single_shot_inference.py: Reduce torch.cuda.synchronize() to
  every 20 steps instead of every step. Gate per-layer diagnostics
  to li<3 or li>=58 (avoid 61 .item() calls per decode step).

2026-06-01 22:21:12 +00:00

15 KiB

Raw Blame History

View Raw