support for newer checkpoints

[binghanc]

What does this PR do?

Type of change: new feature

Overview: support for newer checkpoints

Usage

torchrun --nproc-per-node=8 ptq.py --mla_quant nvfp4_wq_a_wkv_a_wq_b_wo_fp8_wkv_b --batch_size 4 --model_path $DS_CKPT --config DeepSeek-V3/inference/configs/config_671B.json --quant_cfg NVFP4_DEFAULT_CFG --output_path $AMAX_PATH

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.