biondizzle 4d4cfa6b28 fix: tqdm over MoE layer warmup, compile every layer, no print spam ...

The outer loop tqdm now covers the full finalize_weights + warmup for
each MoE layer. CuTeDSL caches by (M,N,K) so every layer shape gets
compiled during warmup — no RPC timeouts during inference.

  (JIT compile)NVFP4 MoE layers:  50%|██████████░░░░░░░░░░| 31/61

2026-05-16 05:21:11 +00:00

..

patches

fix: tqdm over MoE layer warmup, compile every layer, no print spam

2026-05-16 05:21:11 +00:00

nvfp4_cutedsl.py

fix: L1 gate/up split — intermediate_size is per-projection, not fused

2026-05-16 04:04:40 +00:00