NVFP4 Loading support

[yiliu30]

No description provided.

[yiliu30]

Local tests passed:

==================================== PASSES ====================================
=========================== short test summary info ============================
SKIPPED [1] test/test_cuda/test_transformers.py:166: test requires Intel Extension for PyTorch to be installed and match current PyTorch version, see https://github.com/intel/intel-extension-for-pytorch
SKIPPED [1] test/test_cuda/test_transformers.py:136: test requires multiple CUDA GPUs
SKIPPED [1] test/test_cuda/test_transformers.py:101: test requires Intel Extension for PyTorch to be installed and match current PyTorch version, see https://github.com/intel/intel-extension-for-pytorch
============ 6 passed, 3 skipped, 17 warnings in 180.40s (0:03:00) =============


==================================== PASSES ====================================
_______________________ test_e2e_quant_and_infer[mxfp8] ________________________
------------------------------ Captured log call -------------------------------
WARNING  bitsandbytes.cextension:cextension.py:94 Could not find the bitsandbytes CUDA binary at PosixPath('/home/yliu7/miniforge3/envs/ao/lib/python3.11/site-packages/bitsandbytes/libbitsandbytes_cuda128.so')
WARNING  bitsandbytes.cextension:cextension.py:101 The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
=================== 3 passed, 1 warning in 240.91s (0:04:00) ===================