Description of errors
At least some of the docstrings in fused_fp8_quant.py are misleading.
I haven't walked through all of them, but fused_rms_fp8_per_tensor_static_quant documents 6 return values but only returns 4, and fused_rms_fp8_group_quant lists 6 return values but returns 4 values where one is a tuple of 2 values.
Attach any links, screenshots, or additional evidence you think will be helpful.
No response