is deepspeed inference now supporting llama2 replace_with_kernel_inject=True?

[liveforfun]

I tried to inference with replace_with_kernel_inject=True option with llama2-70b.
but I got some errors.
as far as I know replace_with_kernel_inject=True this option is injecting the high-performance kernels.
but it might be not supporting now right?

[RezaYazdaniAminabadi]

Hi @liveforfun

I am adding the support for this here: #4313
Best,
Reza