xFasterTransformer issues

[Kernel] Add GPU kernels.

changqi1

enhancement

gpu

[Layers] Fixed the seg fault error when running with more than 4 ranks

abenmao

[Distribute] Add distribute support for continuous batching api.

1

Master and slaves should both run according to the following workflow: ```Python while True: model.set_input_cb() model.forward_cb() model.free_seqs() ```

Duyi-Wang

enhancement

continuous batching

[Kernel] Add FP16 MHA and MLP kernels.

```bash # weight only FP16 (input FP32, weight FP16, output FP32) [INFO] First token time: 148.062 ms [INFO] Second token time: 48.3581 ms [INFO] Final output is: ============================================== Once upon...

changqi1

enhancement