FP8BlockQuantizer not work on TE

Describe the bug

1. Issues Caused by Enabling Tensor Parallelism (TP)
   Phenomenon: When enabling fp8_recipe == blockwise with TP:

• Error: AssertionError: All-gather requires quantizable tensor for quantizer Float8BlockQuantizer
• If this assertion is commented out and SP (Sequence Parallelism) is disabled:
  Error: ValueError: When using expert parallelism and tensor parallelism, sequence parallelism must be used
• If this assertion is commented out and SP is enabled:
  Error: CUDA Error: an illegal memory access was encountered
  Temporary Solution: Disable TP for MOE training.

2. Issues Caused by Enabling CPU Offload
   If optimizer_cpu_offload is enabled, it requires:

• Not enabling --fp8-param-gather
• And args.fp8_recipe == "delayed"
  Problem: If --fp8-param-gather is not enabled, FP8 training ends up requiring higher GPU memory than BF16 training.

Environment details

If NVIDIA docker image is used you don't need to specify these.
Otherwise, please provide:

• Pytorch version 2.8.0+cu129
• Python version 3.12
• Transformer Engine version 2.8.0
• CUDA version 12.9

Start by reproducing the FP8 blockwise cases described with tensor parallelism, sequence parallelism, expert parallelism, and CPU offload using the stated PyTorch, Transformer Engine, and CUDA versions. Done means the affected configurations no longer produce the quantizer assertion, sequence-parallelism error, illegal memory access, or the reported CPU-offload limitations.