Buckets:
| W0613 17:13:00.785000 24135 torch/utils/_pytree.py:630] <enum 'KernelPreference'> is an Enum subclass and is now natively supported by torch.compile as an opaque value type. Calling register_constant() on Enum subclasses is deprecated and will be an error in a future release. | |
| W0613 17:13:00.810000 24135 torch/utils/_pytree.py:630] <enum 'ScaleCalculationMode'> is an Enum subclass and is now natively supported by torch.compile as an opaque value type. Calling register_constant() on Enum subclasses is deprecated and will be an error in a future release. | |
| Unable to import `torchao` Tensor objects. This may affect loading checkpoints serialized with `torchao` | |
| === save real NVFP4 W4A4 r64 -> outputs/nvfp4/deploy/klein4b_nvfp4_w4a4_r64.safetensors === | |
| Loading pipeline components...: 0%| | 0/5 [00:00<?, ?it/s] Loading pipeline components...: 20%|██ | 1/5 [00:00<00:02, 1.76it/s] Loading pipeline components...: 40%|████ | 2/5 [00:00<00:01, 2.64it/s] Loading pipeline components...: 60%|██████ | 3/5 [00:02<00:01, 1.09it/s] | |
| Loading weights: 0%| | 0/398 [00:00<?, ?it/s][A | |
| Loading weights: 11%|█ | 42/398 [00:00<00:01, 337.44it/s][A | |
| Loading weights: 22%|██▏ | 87/398 [00:00<00:00, 380.95it/s][A | |
| Loading weights: 32%|███▏ | 127/398 [00:00<00:00, 388.45it/s][A | |
| Loading weights: 42%|████▏ | 168/398 [00:00<00:00, 390.73it/s][A | |
| Loading weights: 53%|█████▎ | 211/398 [00:00<00:00, 396.72it/s][A | |
| Loading weights: 68%|██████▊ | 269/398 [00:00<00:00, 452.39it/s][A | |
| Loading weights: 79%|███████▉ | 315/398 [00:00<00:00, 429.35it/s][A | |
| Loading weights: 91%|█████████ | 362/398 [00:00<00:00, 438.46it/s][A Loading weights: 100%|██████████| 398/398 [00:00<00:00, 433.27it/s] | |
| Loading pipeline components...: 100%|██████████| 5/5 [00:04<00:00, 1.08s/it] Loading pipeline components...: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s] | |
| teacher gen (reference)... | |
| 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 6.99it/s] 100%|██████████| 4/4 [00:00<00:00, 12.90it/s] 100%|██████████| 4/4 [00:00<00:00, 12.13it/s] | |
| 0%| | 0/4 [00:00<?, ?it/s] 75%|███████▌ | 3/4 [00:00<00:00, 16.35it/s] 100%|██████████| 4/4 [00:00<00:00, 14.56it/s] | |
| /usr/local/lib/python3.11/dist-packages/nunchaku/lora/flux/utils.py:93: UserWarning: Using a non-tuple sequence for multidimensional indexing is deprecated and will be changed in pytorch 2.9; use x[tuple(seq)] instead of x[seq]. In pytorch 2.9 this will be interpreted as tensor index, x[torch.tensor(seq)], which will result either in an error or a different result (Triggered internally at /pytorch/torch/csrc/autograd/python_variable_indexing.cpp:347.) | |
| result[[slice(0, extent) for extent in tensor.shape]] = tensor | |
| converted 120 Linears in 470s | |
| SAVED -> outputs/nvfp4/deploy/klein4b_nvfp4_w4a4_r64.safetensors (2.67GB) | |
| quant gen (correctness check)... | |
| 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 6.68it/s] 100%|██████████| 4/4 [00:00<00:00, 17.15it/s] | |
| 0%| | 0/4 [00:00<?, ?it/s] 100%|██████████| 4/4 [00:00<00:00, 38.29it/s] 100%|██████████| 4/4 [00:00<00:00, 38.25it/s] | |
| DONE r64 -> outputs/nvfp4/deploy/klein4b_nvfp4_w4a4_r64.safetensors (montages: outputs/nvfp4/deploy/cmp_r64_*.png) | |
Xet Storage Details
- Size:
- 3.61 kB
- Xet hash:
- c4c594040433f33185053be94aab6723ad537280fd58385a326a520cea3ee6bf
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.