v2.2.5 tag. 

tag 2.2.0 post 

tag 2.2.0 post 

tag 2.2.2 post 

v2.2.1 release 

v2.2.0 release 

add high performance moe kernel; fix a16w8 compile bug for sm<80 (#67) 

update sampling, prefix cache, json mode impl (#55) - engine: stop and release model when engine release, and remove deprecated lock - sampling: generate_op heavily modified, remove dependency on global tensors - prefix cache: some bug fix, impove evict performance - json mode: update lmfe-cpp patch, add process_logits, sampling with top_k top_p - span-attention: move span_attn decoderReshape to init - lora: add docs, fix typo - ubuntu: add ubuntu dockerfile, fix install dir err - bugifx: fix multi-batch rep_penlty bug