Recommended FP8 recipe for Blackwell (B200)? Per-tensor `FP8_DEFAULT_CFG` underperforms BF16 at prefill; NVFP4 much faster. Also: exported FP8 checkpoint has no KV `q/k/v_scale`

Describe the bug

Quantizing Mistral-24B with hf_ptq.py for B200/vLLM deployment. Per-tensor static FP8 (FP8_DEFAULT_CFG)
is net slower than BF16 in vLLM (prefill ~2× slower; decode faster), whereas NVFP4 (--qformat nvfp4) is
~2× faster than FP8 and beats BF16 on all metrics. Want to confirm the recommended recipe and understand two
export details.

Steps/Code to reproduce bug

Env: B200 sm_100, modelopt 0.46.0, vLLM 0.25.1 + FlashInfer 0.6.13. Calib 1024 samples @ seq 2048.

Quantization command (hf_ptq.py):

# per-tensor FP8:
python examples/hf_ptq/hf_ptq.py \
  --pyt_ckpt_path <bf16-mistral-24b> \
  --export_path ./mistral_fp8 --qformat fp8 \
  --dataset <custom-calib-dataset> --calib_size 1024 --calib_seq 2048

# NVFP4 (identical, only --qformat and --export_path change):
python examples/hf_ptq/hf_ptq.py \
  --pyt_ckpt_path <bf16-mistral-24b> \
  --export_path ./mistral_nvfp4 --qformat nvfp4 \
  --dataset <custom-calib-dataset> --calib_size 1024 --calib_seq 2048

Bench (vllm bench serve, random 300in / 64out, conc 64):

Long prompts (2048in/64out, conc 32): per-tensor FP8 15.6 req/s vs NVFP4 23.1 req/s.
vllm bench command:
vllm bench serve --model <model-path> --host <host> --port <port> --dataset-name random --random-input-len 300 --random-output-len 64 --num-prompts 1000 --max-concurrency 64'
Note that I have issues on other models quantized in the same way and served through Tensorrt with the torch backend as well.

Expected behavior

I expect fp8 models to go faster than bf16, both with quantized and not quantized kv cache

System information

• Container used (if applicable): docker
• GPU name (e.g. H100, A100, L40S): B200
• Library versions (if applicable):
  • Python: 3.12.3
  • ModelOpt version or commit hash: 0.46.0
  • CUDA: 13.0
  • PyTorch: 2.13.0
  • Transformers: 5.12.1